Emotion probe persistence (token-0 to token-100 correlation) in Cogito v2.1 is 0.214, compared to 0.099 for random unit vectors in 7168D space.

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

• Cogito emotion probe residual autocorrelation +0.077 above variance-matched controls (p=1.5e-27, 157/171 probes positive)finding0.859
  Demonstrates that Cogito emotion probes are persistently active beyond what is explained by their variance alone
• In Cogito v2.1, average residual persistence above variance-matched probes is +0.077 (p = 1.5e-27, 157 of 171 probes positive).finding0.836
  Demonstrates emotion-specific persistence beyond variance effects in Cogito
• SAE emotion subspace overlap correlates with variance-residualized persistence in Cogito: Spearman +0.413, p = 4.4e-196.finding0.824
  Strong positive relationship between emotion alignment and SAE feature persistence in Cogito
• SAE feature emotion subspace overlap correlates with persistence in Cogito: Spearman +0.413, p=4.4e-196finding0.817
  Demonstrates that SAE features more aligned with the emotion subspace are more persistent in Cogito after variance control
• 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.finding0.793
  Supports that persistence is genuinely tied to emotion structure rather than measurement artifact
• 48 of 171 emotion probes individually significant at token 100 post-steeringfinding0.787
  Shows that causal steering effects persist over long ranges for a substantial fraction of emotion probes
• 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.hypothesis0.776
  Falsifiability test built into the PC analysis design
• Persistence is not an artifact of probe construction because lower (more central) emotion PCs are more persistent than noisier high-rank PCsclaim0.776
  Rules out measurement artifact explanation for the persistence finding