self-critical - Story 127677 | Emotion Vectors in Gemma4-31B

The news about Professor Bell’s departure hit Chloe like a ton of bricks. She sat in her chair, paralyzed. The feeling was a familiar one: a tight coil in her gut, a prickling heat under her skin. She had always been...lacking.

She went to the gym, hoping to sweat out the feelings. She ran until her legs burned, pushed herself until she could barely breathe. But the internal tension remained, a persistent ache.

She avoided her friends, unable to face them. Her failures felt magnified, laid bare. She couldn't shake the feeling that she had brought this upon herself.

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:

`L`	0.748
`S`	0.662
`ness`	0.425
`ly`	0.374
`탓`	0.351

Suppressed:

`la`	-0.492
`soon`	-0.304
`(!)`	-0.301
`secured`	-0.284
`cautiously`	-0.280