self-critical - Story 127153 | Emotion Vectors in Gemma4-31B

The email arrived at 11:37 AM. She read the subject line, her breath hitching. Her heart hammered against her ribs, a frantic bird trapped in a cage. Rejected. She knew it. Of course she knew it.

She clicked the email open. The words blurred. "Thank you for your interest..." The polite platitudes felt like a slap in the face. She glanced at the adjacent email in her inbox: from Mark, the friend she’d been competing with. He’d received an offer.

She deleted the email without reading further, the screen reflecting her pale face. The world seemed to tilt on its axis. She felt a profound sense of failure, like the ground had crumbled beneath her feet.

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