self-critical - Story 127579 | Emotion Vectors in Gemma4-31B

The cold steel of the train against his back did nothing to alleviate the chill within him. He'd travelled miles to see Rachel, armed with stories, old photos and a hopeful heart. But Rachel had no memory of him. Their time together was just a smudge in the back of her mind. He was unworthy of notice. He hadn't made a mark on her life. He watched the city lights blur past, a tear escaping and tracing a path down his cheek. He had made her forget.

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