concept
active
concept:emotion-geometry-in-llm-activationsEmotion geometry in LLM activations
Emotion emerges early, peaks in middle layers, sharpens with scale, and persists across tokens in LLM activations per Zhang & Zhong 2025
Neighborhood — ranked by edge-count
Papers (1)
paper
Thinkers (1)
thinker
- Jingxiang ZhangintroducesShowed emotion is geometrically structured in LLM activations; foundational characterization of emotion geometry
Concepts (1)
concept
- Emotive states in LLMsassociated_withDirections in activation space associated with contrastive emotive concept pairs studied in this paper as targets for introspection
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.
- Internal representations encoding emotion concepts in large language models, identified by probing and SAE methods
- Core definition.
- Illustrates how the same empirical finding is read differently by computational functionalists and organismic functionalists.
- If LLM emotion representations resemble human valence-arousal space, behavior and activations will follow distances in that spacehypothesis0.783Prediction from circumplex theory.
- Key finding.
- Question raised by Anthropic and partially addressed by this paper's persistence evidence
- Mechanistic question AOs can't answer.
- Sanity check, not surprising.