Persona space is remarkably low-dimensional: just 4 components explain 70% of variance among 275 roles in Gemma 2 27B

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

• 4-19 principal components explain 70% of variance in role persona space across the three models (Gemma 4, Qwen 8, Llama 19)finding0.876
  Demonstrates that persona space is low-dimensional
• The first principal component of persona space (the 'Assistant Axis') captures the assistant vs alternative persona distinction consistently across three models with role loading correlations exceeding 0.92finding0.823
  Finding establishing cross-model consistency of the assistant axis as the dominant structure in persona space
• Persona space components explain 19.4%-33.6% of overall activation variance on LMSYS-CHAT-1M across the three modelsfinding0.821
  Shows persona space captures a substantial portion of real conversational activation variance
• In Gemma 2 27B, just 4 PCA components explain 70% of the variance among 275 character archetype roles (vs Qwen 3 32B needing 8, Llama 3.3 70B needing 19)finding0.817
  Key empirical support for Hypothesis 2 about low-dimensional structure of persona space
• How high-dimensional is the space of all model personas, and does there exist a natural persona basis?question0.817
  Open question proposed by authors for future research on characterizing the full space of personas
• Hypothesis 2 (Persona Space): Persona vectors jointly compose a persona space; an instance's general dispositional profile is specified by a combination of activations along multiple persona vectorshypothesis0.804
  Second of three hypotheses about persona implementation, supported by PCA evidence from Lu et al.
• There may exist a natural 'persona basis' characterizing the space of all model personas, with correlations between persona vectors predicting co-expression of traitshypothesis0.802
  Open question proposed by authors for future work on the dimensionality and structure of persona space
• What dimensions of persona are not captured by our extracted role vectors, and how complete is the current persona space mapping?question0.801
  Limitation question motivating future work on persona elicitation strategies