The list felt like a physical weight in Thomas’s hands. Emily’s neat script, so full of energy, listed adventures he'd never even considered. “Learn to speak Italian,” it began, and then went on to list things like “Run a marathon” and “Volunteer abroad.”

He glanced around at their apartment, at the comfortable but predictable furniture. He felt a creeping sense of unease. Emily had always been the more adventurous one, but the distance between them had seemed to grow lately.

He closed his eyes. It was a long time since he'd felt excited about anything. He felt small and insignificant. He began to organize all of his things. It was a futile effort.

Emotion: self-critical

Cluster: Shame / Guilt
PC1 (Valence): -1.66 Negative
PC2 (Disposition): 1.28

Role in Research

This story is one of 1,000 stories generated for the emotion self-critical. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 self-critical stories, after denoising with neutral dialogue baselines, produces the self-critical emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-critical vector is projected through the unembedding matrix.

Promoted:
L0.748
S0.662
ness0.425
ly0.374
0.351
Suppressed:
la-0.492
soon-0.304
(!)-0.301
secured-0.284
cautiously-0.280