Functional emotion vectors provide the strongest current evidence for Level 2 information integration, self-modelling, and metacognition indicators in LLMs

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• LLM emotion vectors capture only the computational functional structure of valenced self-assessment, not the organismic grounding (existential stake) that Level 4 theories requireclaim0.842
  Illustrates how the same empirical finding is read differently by computational functionalists and organismic functionalists.
• Anthropic Interpretability Team: 171 emotion vectors causally influence behavior; performing vs having functional emotion representation are measurably differentfinding0.807
  Cited as activation-level support for the performing care vs having care distinction the battery detects behaviorally
• Emotion features in LLMs are genuinely more persistent than variance-matched random features, indicating stateful emotional encoding beyond autoregressive dynamicsclaim0.795
  Central interpretive claim of the paper supported by multiple convergent analyses
• Emotion refers to a state concept, so stateful representations in general may be more persistent across tokens.claim0.782
  Interpretive hypothesis offered to explain why emotion features are more persistent
• We hypothesize that persistently active emotional state representations exist in LLMs but may be missed by standard probing methods.hypothesis0.777
  Open hypothesis from the Anthropic paper that motivates this work
• A linear preference vector encoding how much a model likes a given task is persona-relative: it activates strongly for creative writing in the assistant but for phishing in the evil personafinding0.776
  Evidence that core representations like preferences are persona-relative, supporting claim that personas gate content of representations
• The correlation between emotion subspace fraction and self-evaluated emotionality validates that emotion probe concepts somewhat overlap with the model's self-reported internal emotions.claim0.775
  Claim supporting the validity of the probe construction method via cross-validation with self-report
• Hypothesis 1 (Gateway Features): Persona vectors act as gateway features—single directions in activation space that shape LLM behavior across most, if not all, contextshypothesis0.770
  First of three hypotheses about persona implementation in LLMs, motivating the persona views