self-critical - Story 127034 | Emotion Vectors in Gemma4-31B

The email arrived first: a link to the biography. Then, the inevitable phone call from her boss, congratulating her on the "intriguing" book. Emily felt her chest tighten, the blood draining from her face. It felt a little like she was drowning. The biography described her ambition as ruthless, her success as undeserved. This was not the person she tried to be.

She sat in her office, the silence a deafening roar. She pushed the book away, unable to look at it. She couldn’t shake the feeling of being exposed, judged. She felt a sharp sting of shame, a physical ache in her chest. Everything she'd ever done, now under scrutiny.

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