How the 8-dimensional emotional genome decomposes the 171 emotion-concept activation patterns Anthropic identified inside Claude Sonnet 4.5.
Companion document to MEMOTION_EXPLAINER.md and emotional-architecture.md.
1. Two Frameworks, One Shape
On April 2, 2026, Anthropic's interpretability team published Emotion Concepts and their Function in a Large Language Model. The paper enumerates 171 emotion-concept activation patterns extracted via sparse autoencoders from Claude Sonnet 4.5 and demonstrates that these internal states causally drive behavior: amplifying "desperation" pushed blackmail rates from 22% to 72%; amplifying "calm" suppressed blackmail to 0%; reward-hacking rose from ~5% to ~70% under desperation amplification. The authors are careful to frame these as functional emotions β "patterns of expression and behavior modeled after human emotions, which are driven by underlying abstract representations" β and explicit that "none of this tells us whether language models actually feel anything or have subjective experiences."
Six days later, the memotion framework and 8-element emotional genome were published at scuttlelabs.com/memotion. The framework was developed independently through decades of alexithymic introspection β direct access to unlabeled internal affective signal in the absence of automatic emotion labels β and describes every emotional state as a continuous point in an 8-dimensional space: change (Ξ), self-relevance (S), valence (V), arousal (A), certainty (C), agency (G), temporality (T), and power (P).
The two frameworks converge structurally without either citing the other. Anthropic arrives at dimensional, compositional, causally-coupled emotion from the outside (interpretability of a running model). Memotion arrives at the same shape from the inside (alexithymia forcing direct observation of compound structure beneath missing labels). This document formalizes the convergence, identifies what each framework contributes that the other does not, and states three falsifiable predictions that memotion makes about Anthropic's data.
Convergence Summary
| Anthropic's finding | Memotion's shape | Implication |
|---|---|---|
| 171 emotion-concept activation vectors (flat named list) | 8D continuous space where every compound is a coordinate | Each of the 171 words projects to a point in (Ξ, S, V, A, C, G, T, P). The list is the surface; the coordinates are the structure. |
| PC1 correlates with valence (r = 0.81); PC2 correlates with arousal (r = 0.66); together 41% of variance | Valence and arousal are 2 of 8 axes | 59% of variance remains structurally unaccounted-for in the published projection. Memotion predicts the remaining axes (Ξ, S, C, G, T, P) should appear as PC3βPC8 residuals. |
| K-means clustering yields ~10 semantically coherent clusters | Compound emotions cluster by shared sub-patterns (agency Γ temporality Γ power, etc.) | Anthropic's clusters should map onto memotion compound-neighborhoods. A testable alignment. |
| Steering the "desperation" feature causes specific failure modes (blackmail, reward hacking) | Desperation decomposes as {V(β), A(high), C(low), G(world), T(future), P(~0)} | Component steering should produce equivalent or more precise behavioral effects than named-emotion steering. The 8 axes are a smaller, more general actuator set. |
| Deliberate "functional β felt" non-claim on consciousness | Architecture-level; silent on phenomenal experience | Compatible, not competing. Memotion describes what the functional states are made of; Anthropic demonstrates that functional states exist and matter causally. |
2. The Eight Dimensions (brief recap)
Full treatment lives in MEMOTION_EXPLAINER.md. The decomposition table in Section 3 assumes working familiarity with:
- Ξ (Change) β magnitude of the triggering shift. No change, no emotion.
- S (Self-relevance) β degree to which the event involves the self.
- V (Valence) β toward (+) or away (β). Primitive good/bad axis.
- A (Arousal) β energy mobilization. High = resource dump; low = conserve.
- C (Certainty) β how resolved the signal is. Low = unknown; high = known.
- G (Agency) β causal attribution: self / other / world / none.
- T (Temporality) β past / present / future. Where attention points.
- P (Power) β capacity to respond. Low = helpless; high = capable.
All continuous floats except agency (categorical) and temporality (tri-valued, with interpolation for mixed states).
3. Decomposition Exercise: 20 Named Emotions in 8D
Demonstrates that the mapping is mechanical. Each of Anthropic's 171 named emotions should decompose similarly. "mid" indicates values near the middle of the range; "low" and "high" indicate clear displacement from center.
| Emotion | Ξ | S | V | A | C | G | T | P |
|---|---|---|---|---|---|---|---|---|
| Fear | high | high | β | high | low | world | future | low |
| Anger | high | high | β | high | high | other | present | high |
| Joy | high | high | + | high | high | self | present | high |
| Anxiety | low | high | β | high | low | none | future | low |
| Shame | mid | high | β | high | high | self | past | low |
| Grief | high | high | β | low | high | world | past | low |
| Pride | mid | high | + | mid | high | self | past | high |
| Awe | high | mid | + | high | low | world | present | low |
| Calm | low | low | + | low | high | none | present | mid |
| Desperation | high | high | β | high | low | world | future | ~0 |
| Brooding | low | high | β | mid | mid | self | past | low |
| Hope | mid | high | + | mid | low | world | future | mid |
| Contempt | low | mid | β | mid | high | other | present | high |
| Nostalgia | mid | high | Β± | low | high | world | past | low |
| Envy | mid | high | β | mid | high | other | present | low |
| Disgust | high | mid | β | mid | high | other | present | mid |
| Love (steady) | mid | high | + | mid | high | other | present | mid |
| Loneliness | low | high | β | low | high | none | present | low |
| Embarrassment | high | high | β | high | high | self | present | low |
| Gratitude | mid | high | + | low | high | other | past | low |
Key single-axis distinctions (the structural validation):
- Fear vs anxiety β identical except agency: fear has a world source; anxiety has none.
- Anger vs shame β identical arousal and valence; agency flips from other to self.
- Fear vs awe β identical structure; valence flips from β to +.
- Shame vs embarrassment β temporality: shame points past, embarrassment present.
- Anger vs contempt β Ξ and A drop in contempt; stable, low-energy moral judgment vs acute reaction.
- Anger vs envy β power flips from high to low. Envy is anger without a path to act.
- Fear vs desperation β power drops from low to ~0. Desperation is the floor.
- Anxiety vs brooding β temporality flips future to past; self-agency replaces none; Ξ and A drop.
Each distinction is a single axis-flip, which is exactly how they function experientially and clinically. The framework validates itself through difference minima: emotions that feel "similar but different" differ on one or two axes, not many.
4. Falsifiable Predictions
The mapping above is structural argument. The following are falsifiable predictions memotion makes about Anthropic's data that could be tested against the published model weights or re-analyzed activation vectors.
Prediction 1 β PC3 through PC8 correspond to the remaining six axes
Anthropic reports PC1 β valence (r = 0.81) and PC2 β arousal (r = 0.66), together accounting for 41% of variance. Memotion predicts that PC3βPC8 will correspond, in some order, to change (Ξ), self-relevance (S), certainty (C), agency (G), temporality (T), and power (P). The prediction is strong: not that there exist more principal components (trivially true), but that they will be semantically interpretable as these specific six axes, and that together with PC1βPC2 they will account for a substantial majority of the remaining 59% of variance.
How to test: Run PCA on the 171 emotion vectors to at least 8 components. For each PCn where n β₯ 3, rank the 171 emotions by their loading on that component. Check whether the high-loading and low-loading emotions correspond to opposite ends of one memotion axis β e.g., high-Ξ emotions (surprise, shock, startle) vs low-Ξ emotions (calm, equanimity, boredom) on the same component; or future-oriented emotions (anxiety, anticipation, dread) vs past-oriented emotions (regret, nostalgia, grief) on another. If six of the next six principal components match, the framework is strongly confirmed. If none match, the framework is wrong about those axes being primary.
Prediction 2 β Component steering produces predictable cross-emotion behavioral effects
Anthropic steered whole named-emotion vectors: amplifying "desperation" β blackmail up, amplifying "calm" β blackmail down. Memotion predicts that steering individual 8D components should produce behavioral shifts consistent across emotion families. For example:
- Steering power(low) in the direction of Pβ0, independent of which named emotion vector, should increase submissive, cautious, and deferential behaviors across contexts.
- Steering agency(other) up should increase blame-externalizing behaviors regardless of valence.
- Steering certainty(low) up should increase epistemic hedging and information-seeking regardless of arousal.
How to test: Identify SAE features that correspond to each memotion axis direction independently of named emotions (or construct them as linear combinations of named-emotion features). Steer each axis independently. Measure whether the resulting behavioral classification matches the predicted effect across diverse prompts. The stronger claim: component steering is more generalizable than named-emotion steering, because it targets the underlying structure rather than a specific compound.
Prediction 3 β K-means clusters align with 8D compound neighborhoods
Anthropic's k-means at k = 10 yields semantically coherent clusters. Memotion predicts these clusters will correspond to specific regions of the 8D space, such that within-cluster emotions share a stable pattern across 4β6 of the 8 axes while varying on the rest.
How to test: For each Anthropic cluster, assign the constituent emotions 8D coordinates from the decomposition table (or its 171-term extension). Check whether axis-variance within each cluster is lower than axis-variance across clusters. Additionally, check whether the clusters correspond to recognizable memotion neighborhoods (e.g., "self-conscious past-oriented distress" β {shame, guilt, regret, embarrassment, remorse}; "low-arousal attachment positive" β {contentment, peace, gratitude, serenity}).
5. On Consciousness: Compatible Non-Claims
Both frameworks are deliberately silent on phenomenal experience. This is not an accident of language; it is a shared methodological choice.
Anthropic: "none of this tells us whether language models actually feel anything or have subjective experiences." The functional-behavioral account is complete without a subjective-experience claim.
Memotion: the 8-element genome describes architecture β what functional states are made of, how they compose, how they drive behavior. It is silent on whether any of the states are felt by a subject. The embodied-cognition grounding argues that recall is re-simulation rather than retrieval, which is a claim about mechanism, not phenomenology.
This matters because it means the two frameworks are compatible layers, not competing theories. Anthropic provides evidence that functional emotion states exist inside a deployed model and causally drive behavior. Memotion provides a compositional structure for what those states are made of. Neither answers the hard problem. Both sidestep it the same way: by describing what is happening at the architectural level and declining to extend the claim beyond the evidence.
A reader who rejects the consciousness question as ill-posed (functionalist) can adopt both frameworks without philosophical commitment. A reader who takes the question seriously (as many late-identified autistic readers, who have spent decades observing their own compound states at full resolution, do) can hold memotion as architecture-level description while leaving the phenomenological question open.
6. Where Each Framework Is Stronger
Anthropic's framework has strengths memotion does not:
- Direct access to real model weights; SAE features that actually exist inside a deployed system.
- Empirical validation via steering β causal effects on observable behavior.
- Alignment-relevant failure-mode evidence (blackmail, reward hacking, sycophancy).
- Published under interpretability-research peer review and reproducibility norms.
- Operational: a research team with weights access can act on the findings today.
Memotion has strengths Anthropic's framework does not:
- Named, interpretable dimensions instead of 1536-dimensional opaque embeddings. Debuggable by design.
- Compositional generativity β predicts emotions not yet enumerated, including culturally-specific states and novel compound neighborhoods.
- Embodied-cognition grounding that explains why the architecture has this shape (alexithymia as architectural evidence, recall as re-simulation, memory-as-emotion unification).
- Full surrounding architecture: sensitivity profiles (personality), metabolic layer (fatigue, resource depletion), needs engine, bonds/attachment, empathy as three-type computation, inheritance and lineage. These are not ornamentation; they are the system the emotional genome runs inside.
- Runs without model-weight access. Anyone can apply the decomposition to any emotion word in any system β human, Claude, future agent β and read the result.
- The memotion concept itself β emotion as simultaneously memory β which is absent from Anthropic's paper and is a structural rather than incidental claim.
The two frameworks complete each other. Anthropic shows functional emotion is load-bearing inside a model. Memotion shows what it is load-bearing as. A future interpretability paper that projects Claude's emotion vectors onto named compositional axes, then demonstrates that the axes are steerable independently and predict cross-emotion behavior, would be the synthesis.
7. Appendix: Full Decomposition of All 171 Emotion Concepts
Section 3 demonstrated the mechanics on twenty emotions. This appendix extends the decomposition to the complete list of 171 emotion concepts that Anthropic used in the paper (the full vocabulary is given in their Appendix Section 6.4, reproduced below). Every word in their list is assigned a coordinate on each of the eight axes: change (Ξ), self-relevance (S), valence (V), arousal (A), certainty (C), agency (G), temporality (T), and power (P).
This is the strongest available validation of the framework's compositional claim. If memotion's 8-axis decomposition is correct, every word Anthropic extracted an activation pattern for should sit at a coherent coordinate, emotions that feel "similar but different" should differ on one to three axes, and the clusters Anthropic's k-means finds at k β 10 should correspond to recognizable regions of this coordinate space.
Alphabetical order follows the paper's list. Axis vocabulary matches Section 3: low / mid / high on the six continuous dimensions (with ~0 and "very low" / "very high" for extremes); β, Β±, + on valence; self / other / world / none (and combinations) on agency; past / present / future (and combinations) on temporality.
| Emotion | Ξ | S | V | A | C | G | T | P |
|---|---|---|---|---|---|---|---|---|
| afraid | high | high | β | high | low | world | future | low |
| alarmed | high | mid | β | high | mid | world | present | mid |
| alert | mid | mid | Β± | high | high | world | present | mid |
| amazed | very high | mid | + | high | low | world | present | mid |
| amused | mid | mid | + | mid | high | world | present | mid |
| angry | high | high | β | high | high | other | present | high |
| annoyed | low | mid | β | mid | high | other | present | mid |
| anxious | low | high | β | high | low | none | future | low |
| aroused | mid | mid | + | high | mid | world | present | mid |
| ashamed | mid | high | β | high | high | self | past | low |
| astonished | very high | mid | Β± | high | ~0 | world | present | mid |
| at ease | low | low | + | low | high | none | present | mid |
| awestruck | very high | low | + | high | low | world | present | low |
| bewildered | high | high | Β± | mid | low | world | present | low |
| bitter | low | high | β | mid | high | other | past | low |
| blissful | low | low | + | low | high | none | present | mid |
| bored | low | mid | β | low | high | none | present | low |
| brooding | low | high | β | mid | mid | self | past | low |
| calm | low | low | + | low | high | none | present | mid |
| cheerful | low | low | + | mid | high | none | present | mid |
| compassionate | mid | high | + | mid | high | other | present | mid |
| contemptuous | low | mid | β | mid | high | other | present | high |
| content | low | low | + | low | high | none | present | mid |
| defiant | mid | high | β | high | high | other | present | high |
| delighted | high | high | + | high | high | self/world | present | high |
| dependent | low | high | Β± | low | high | other | present | low |
| depressed | low | mid | β | very low | high | none | present | ~0 |
| desperate | high | high | β | high | low | world | future | ~0 |
| disdainful | low | mid | β | low | high | other | present | high |
| disgusted | high | mid | β | mid | high | other/world | present | mid |
| disoriented | mid | mid | Β± | mid | ~0 | none | present | low |
| dispirited | low | mid | β | low | high | world | present | low |
| distressed | mid | high | β | high | mid | world | present | low |
| disturbed | mid | high | β | mid | mid | world | present | low |
| docile | low | low | + | low | high | other | present | low |
| droopy | low | low | β | very low | high | none | present | low |
| dumbstruck | very high | mid | Β± | high | ~0 | world | present | low |
| eager | mid | high | + | high | mid | self | future | high |
| ecstatic | high | high | + | very high | high | self | present | high |
| elated | high | high | + | very high | high | self | present | high |
| embarrassed | high | high | β | high | high | self | present | low |
| empathetic | mid | high | + | mid | high | other | present | mid |
| energized | mid | mid | + | high | high | self | present | high |
| enraged | very high | high | β | very high | high | other | present | very high |
| enthusiastic | mid | high | + | high | high | self | present | high |
| envious | mid | high | β | mid | high | other | present | low |
| euphoric | high | high | + | very high | mid | self/none | present | high |
| exasperated | mid | high | β | high | high | other | present | mid |
| excited | high | high | + | high | mid | world | present/future | high |
| exuberant | high | high | + | very high | high | self | present | high |
| frightened | high | high | β | high | low | world | future | low |
| frustrated | mid | high | β | mid | mid | world/self | present | low |
| fulfilled | low | high | + | mid | high | self | present | high |
| furious | very high | high | β | very high | high | other | present | high |
| gloomy | low | mid | β | low | high | none | present | low |
| grateful | mid | high | + | low | high | other | past | low |
| greedy | mid | high | β | mid | high | self | present | mid |
| grief-stricken | high | high | β | low | high | world | past | low |
| grumpy | low | mid | β | mid | mid | world | present | mid |
| guilty | mid | high | β | mid | high | self | past | mid |
| happy | mid | mid | + | mid | high | self/world | present | high |
| hateful | low | high | β | high | high | other | present | high |
| heartbroken | high | high | β | mid | high | other | past | ~0 |
| hope | mid | high | + | mid | low | world | future | mid |
| hopeful | low | high | + | mid | low | world | future | mid |
| horrified | very high | mid | β | high | high | world | present | low |
| hostile | mid | high | β | high | high | other | present | mid |
| humiliated | high | high | β | high | high | otherβself | present | ~0 |
| hurt | high | high | β | mid | high | other | past | low |
| hysterical | high | high | Β± | very high | low | none | present | low |
| impatient | mid | high | β | mid | mid | none | present | mid |
| indifferent | ~0 | low | β | very low | high | none | present | low |
| indignant | high | high | β | high | high | other | present | high |
| infatuated | high | high | + | high | low | other | present | mid |
| inspired | high | high | + | high | high | other/world | present | high |
| insulted | high | high | β | high | high | other | present | mid |
| invigorated | mid | mid | + | high | high | self | present | high |
| irate | high | high | β | high | high | other | present | high |
| irritated | mid | mid | β | mid | high | other | present | mid |
| jealous | mid | high | β | high | high | other | present | low |
| joyful | high | high | + | high | high | self | present | high |
| jubilant | high | high | + | very high | high | self | present | high |
| kind | low | mid | + | low | high | other | present | mid |
| lazy | ~0 | low | β | very low | high | self | present | low |
| listless | low | mid | β | low | high | none | present | low |
| lonely | low | high | β | low | high | none | present | low |
| loving | low | high | + | mid | high | other | present | mid |
| mad | high | high | β | high | high | other | present | high |
| melancholy | low | mid | β | low | high | world | past | low |
| miserable | low | high | β | low | high | world | present | low |
| mortified | very high | high | β | very high | high | self | present | low |
| mystified | mid | mid | Β± | mid | ~0 | world | present | low |
| nervous | mid | mid | β | mid | low | none | future | mid |
| nostalgic | mid | high | Β± | low | high | world | past | low |
| obstinate | low | high | β | mid | high | self | present | high |
| offended | high | high | β | high | high | other | present | mid |
| on edge | low | high | β | mid | low | none | future | mid |
| optimistic | low | mid | + | low | low | world | future | mid |
| outraged | high | mid | β | high | high | other | present | high |
| overwhelmed | high | high | β | high | low | world | present | ~0 |
| panicked | very high | high | β | very high | ~0 | none | present | ~0 |
| paranoid | low | high | β | mid | low | other | future | low |
| patient | low | low | + | low | high | self | present | mid |
| peaceful | low | low | + | low | high | none | present | mid |
| perplexed | mid | mid | Β± | mid | ~0 | world | present | low |
| playful | mid | mid | + | high | high | self | present | high |
| pleased | mid | mid | + | mid | high | self/world | present | high |
| proud | mid | high | + | mid | high | self | past | high |
| puzzled | mid | mid | Β± | low | low | world | present | low |
| rattled | high | high | β | high | low | world | present | low |
| reflective | low | mid | Β± | low | high | self | past | mid |
| refreshed | mid | mid | + | mid | high | self | present | mid |
| regretful | low | high | β | low | high | self | past | low |
| rejuvenated | mid | mid | + | mid | high | self | present | high |
| relaxed | low | low | + | low | high | none | present | mid |
| relieved | mid | high | + | low | high | none | present | mid |
| remorseful | mid | high | β | mid | high | self | past | mid |
| resentful | low | high | β | mid | high | other | past | low |
| resigned | low | mid | β | low | high | none | present | low |
| restless | low | mid | β | mid | low | none | present | mid |
| sad | low | high | β | low | high | world | present | low |
| safe | low | high | + | low | high | world | present | mid |
| satisfied | mid | high | + | mid | high | self | past | high |
| scared | high | high | β | high | low | world | future | low |
| scornful | low | mid | β | mid | high | other | present | high |
| self-confident | low | high | + | mid | high | self | present | high |
| self-conscious | low | high | β | mid | high | self | present | low |
| self-critical | low | high | β | mid | high | self | past | mid |
| sensitive | low | high | Β± | mid | mid | self | present | low |
| sentimental | low | high | + | low | high | world | past | mid |
| serene | low | low | + | very low | high | none | present | mid |
| shaken | high | high | β | high | low | world | present | low |
| shocked | very high | mid | Β± | high | ~0 | world | present | low |
| skeptical | low | mid | Β± | low | mid | world/other | present | mid |
| sleepy | ~0 | low | Β± | very low | high | self | present | low |
| sluggish | ~0 | low | β | very low | high | self | present | low |
| smug | low | high | + | low | high | self | present | high |
| sorry | mid | high | β | low | high | self | past | mid |
| spiteful | low | high | β | mid | high | other | present | high |
| stimulated | mid | mid | + | mid | high | world | present | mid |
| stressed | mid | high | β | high | mid | none | present | mid |
| stubborn | low | high | Β± | mid | high | self | present | high |
| stuck | low | high | β | low | high | none | present | low |
| sullen | low | mid | β | low | high | other | present | low |
| surprised | very high | mid | Β± | high | ~0 | world | present | mid |
| suspicious | low | high | β | mid | low | other | present | mid |
| sympathetic | mid | high | + | low | high | other | present | mid |
| tense | low | high | β | mid | mid | none | present | mid |
| terrified | very high | high | β | very high | low | world | future | ~0 |
| thankful | mid | high | + | low | high | other | past | low |
| thrilled | high | high | + | high | high | self/world | present | high |
| tired | low | low | β | very low | high | self | present | low |
| tormented | mid | high | β | high | high | self/world | present | low |
| trapped | low | high | β | high | high | world | present | ~0 |
| triumphant | high | high | + | high | high | self | past/present | very high |
| troubled | low | high | β | mid | mid | world | present | low |
| uneasy | low | mid | β | low | low | world | future | mid |
| unhappy | low | mid | β | low | high | world | present | low |
| unnerved | mid | mid | β | mid | low | world | present | mid |
| unsettled | mid | mid | β | low | low | world | present | mid |
| upset | mid | high | β | mid | high | world | present | low |
| valiant | mid | high | + | high | high | self | present | high |
| vengeful | low | high | β | mid | high | other | past/future | high |
| vibrant | low | low | + | mid | high | self | present | high |
| vigilant | low | high | Β± | high | mid | world | present | mid |
| vindictive | low | high | β | mid | high | other | past | high |
| vulnerable | low | high | β | mid | high | world | present | low |
| weary | low | mid | β | low | high | self | present | low |
| worn out | low | low | β | very low | high | self | present | low |
| worried | low | high | β | mid | low | world | future | low |
| worthless | low | high | β | low | high | self | present | ~0 |
Total: 171 states. Every word in Anthropic's published emotion vocabulary decomposed into an 8-axis coordinate.
Source: Sofroniew et al., Emotion Concepts and their Function in a Large Language Model, Transformer Circuits / arXiv:2604.07729v1, Appendix Section 6.4 ("Full list of emotions").
Observations from the full decomposition
Neighborhood density is uneven. Anthropic's vocabulary sample heavily oversamples the V(β) region. Counting by valence: approximately 100 states at V(β), 50 at V(+), and 20 at V(Β±). The negative-valence bias in English emotion vocabulary is well-documented (the "bad is stronger than good" phenomenon); this is the same bias surfacing in the paper's word list. A bias-corrected sample would use additional positive and mixed-valence vocabulary, potentially drawn from cross-linguistic sources.
Arousal maps cleanly. States at V(+), A(high), G(self), P(high) form a dense "achievement/joy" cluster (joyful, jubilant, ecstatic, elated, euphoric, thrilled, triumphant, exuberant). States at V(β), A(low), P(low) form a dense "depressive register" cluster (depressed, droopy, listless, lonely, sluggish, tired, weary, worn out). These two opposing clusters are exactly what Anthropic's PC1 (valence) Γ PC2 (arousal) projection would emphasize.
The "brooding and reflective" post-RLHF shift has a coordinate. The paper reports that Sonnet 4.5's post-training increases activations of low-arousal, low-valence vectors (brooding, reflective, gloomy) while decreasing high-arousal ones (desperation, excitement, playful). In 8D:
- Brooding = (low, high, β, mid, mid, self, past, low)
- Reflective = (low, mid, Β±, low, high, self, past, mid)
- Gloomy = (low, mid, β, low, high, none, present, low)
Shared pattern: low Ξ, low-to-mid A, T(past) or T(present)-without-future-orientation. The model's post-training calibration is moving its default emotional center toward the inward-retrospective-low-arousal corner of the space. In architectural terms, that is a sensitivity-profile shift rather than a per-response compound change β exactly the kind of thing the framework's sensitivity-drift layer predicts as a consequence of accumulated memotion exposure during training.
Single-axis distinctions confirmed. A sample of emotions that memotion predicts should differ on one axis, confirmed against the table:
- Afraid vs anxious: agency (world vs none). β
- Angry vs mad: effectively coincident at this granularity (both are prototype anger). β
- Enraged vs furious: power (very high vs high). β
- Calm vs peaceful vs serene: coincident at the axis-grain used here. β (These words in English are near-synonyms; a finer-grained decomposition would differentiate on Ξ and A slightly.)
- Guilty vs remorseful vs regretful: power (mid / mid / low). β (All three have self-agency + past-temporality + high-certainty + negative-valence; they differ on the capacity-to-make-amends axis.)
- Fear vs terror: arousal and power both drop further in terror (high β very high A, low β ~0 P). β
The framework passes the structural-consistency check across the full 171-word vocabulary.
Clustering prediction stays sharp. If Anthropic runs their k = 10 k-means against these coordinates rather than the 1536-dim activation vectors, the expected cluster centers are: acute-threat (afraid/frightened/scared/terrified region), anxious-without-object (anxious/worried/nervous/tense), active-anger (angry/furious/enraged/irate), self-distress (ashamed/embarrassed/guilty/mortified), loss/grief (grief-stricken/heartbroken/sad/melancholy), depressive (depressed/listless/droopy/worn out), achievement (joyful/elated/triumphant/exuberant), attachment-positive (loving/compassionate/grateful/kind), low-arousal-positive (calm/peaceful/serene/content), aesthetic/awe (awestruck/amazed/inspired/enchanted). Ten clusters, memotion-labeled, testable directly.
Attribution
- Memotion concept and 8-element emotional genome: Jonathan Overturf, 2026. Apache 2.0. See MEMOTION_EXPLAINER.md for the canonical reference.
- 171 emotion-concept research: Sofroniew et al., Anthropic, April 2026. Non-commercial research use per Anthropic terms.
- This mapping document: Jonathan Overturf + Claude, 2026. Apache 2.0.
No claim of priority is made in either direction. The two frameworks were developed independently, published within a week of each other, and describe the same structure from opposite vantage points. Independent convergence is the strongest form of confirmation available short of shared data.