Does sentiment have a higher-dimensional concept cone representation, and if so, what methods could find it?

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

• Concept cone methodology failed to produce a meaningful cone for sentiment on Stanford Sentiment Treebankfinding0.794
  Negative result from sentiment extension showing concept cones do not trivially generalize
• Emotion refers to a state concept, so stateful representations in general may be more persistent across tokens.claim0.771
  Interpretive hypothesis offered to explain why emotion features are more persistent
• If persistence is genuinely related to emotion features, lower PCs of the emotion space (more central, less noisy) should be more persistent; if it is an artifact, noisier PCs should have similar persistence.hypothesis0.758
  Falsifiability test built into the PC analysis design
• We hypothesize that emotion states are more persistent because they correspond to genuinely stateful internal representations, not merely local surface contenthypothesis0.757
  Proposed explanation for why emotion probes are more persistent than variance-matched random probes
• Emotion may refer to a state, and more stateful concepts in general tend to be more persistent across tokens than non-stateful onesclaim0.755
  Proposed mechanistic explanation for why emotion features are more persistent
• Larger models can support higher-dimensional truth cones than smaller modelsclaim0.742
  Interpretation of ASR degradation patterns by model size across cone dimensions
• Individual cone basis vectors may correspond to interpretable semantic facets of truth such as temporal facts, geographic facts, or commonsensehypothesis0.741
  Future direction hypothesis for giving semantic meaning to individual axes
• Lower (more central) PCs of emotion feature activations are more persistent than higher-rank (noisier) PCs in both Kimi and Cogito, above variance-matched baselines.finding0.740
  Supports that persistence is genuinely tied to emotion structure rather than measurement artifact