self-critical - Story 127636 | Emotion Vectors in Gemma4-31B

Julia found the letter hidden in her grandmother’s old sewing box. It was a letter to her late mother, filled with anxieties about her career, her appearance, and, above all, about being loved.

The words were so familiar, so achingly honest. She felt a familiar weight in her chest. She had always felt she would fall short of expectations.

She looked around the room, at the antique furniture and the family portraits on the walls. She felt as though she didn't belong. She closed her eyes, fighting back tears.

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