self-critical - Story 127313 | Emotion Vectors in Gemma4-31B

The coffee shop buzzed with Saturday morning energy, but for Elena, the air felt thick with unspoken things. She’d overheard David talking to his sister on the phone, a conversation sprinkled with words she understood, words that shouldn't be hers to hear. He’d hung up as she approached, a sheepish smile on his face.

She took a long sip of her latte, the bitterness doing little to soothe the tightness in her stomach.

He was already at the table, engrossed in a novel written in her native tongue. Elena found herself assessing him, the way he held the book, the concentration on his face. She wondered if he was better than her at all sorts of things.

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