claim
active
claim:emotion-vectors-encode-locally-operative-emotion-rather-than-persistent-state-persistence-may-be-tracked-via-attentionEmotion vectors encode locally operative emotion rather than persistent state; persistence may be tracked via attention
Interpretation of Part 2.
Source paper
extracted_from(2026) · Nicholas Sofroniew · Isaac Kauvar · William Saunders · Runjin Chen +12
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (3)
finding
- Assistant-colon probe values predict response emotion better than user-turn (r=0.87 vs 0.59)supportsColon token carries prepared emotion.
- Layerwise evolution.
- User and Assistant emotions dissociate.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Interpretive hypothesis offered to explain why emotion features are more persistent
- Proposed explanation for why emotion probes are more persistent than variance-matched random probes
- Linear representations of emotion concepts extracted from activations.
- Core empirical claim distinguishing emotion persistence from generic high-variance probe persistence
- Illustrates how the same empirical finding is read differently by computational functionalists and organismic functionalists.
- Deflection vectors represent not expressing an implied emotion, not an internalized emotional stateclaim0.800Interpretation of deflection.
- Core unresolved confound the paper acknowledges but cannot rule out
- Sanity check, not surprising.