PC1 explains 82% of variance in factor analysis of 2224 data points across 6 scoring dimensions

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

• Factor Analysis on Scoring Dimensionsmethod0.797
  Factor analysis on 2224 data points revealing PC1 explains 82% of variance; six dimensions are not independent
• Pairwise similarity of trait PC1 across all three models is >0.81; no pairwise correlation in top 3 trait PCs is below 0.70finding0.743
  Shows trait space has more cross-model consistency than role space beyond PC1
• Alignment type is the only significant predictor of scores (p=0.006); architecture and parameter count do not.finding0.742
  Kruskal-Wallis test result: Constitutional AI predicts highest baseline; roleplay/empathy training predict lowest.
• Response length (words) correlates with scores at r=0.22 baseline and r=0.12 contemplative; explains only ~5% of variancefinding0.739
  Discriminant validity: composite scores are not reducible to verbosity
• Trait space requires 4 dimensions (Gemma, Qwen) and 7 dimensions (Llama) to explain 70% of variance, with distinctive PC1 spanning conscientious to impulsive traitsfinding0.733
  Corroborates role space findings using traits; shows PC1 also captures Assistant-ness in trait space
• Pairwise correlation of role loadings on PC1 exceeds 0.92 across all model pairs, indicating remarkably high similarity of the Assistant Axis across Gemma, Qwen, and Llamafinding0.731
  Shows the leading component of persona space is model-universal
• Criterion 2: Statistically significant Φ value differences (p<0.05) across ToM score categories via Wilcoxon test.concept0.731
  Second of three operational criteria; requires distributional significance in IIT estimates across performance levels.
• 4-19 principal components explain 70% of variance in role persona space across the three models (Gemma 4, Qwen 8, Llama 19)finding0.727
  Demonstrates that persona space is low-dimensional