self-critical - Story 127303 | Emotion Vectors in Gemma4-31B

The email announcing the salary adjustments hung in her inbox, a digital noose. Beneath the bland corporate language, she felt the sting of humiliation. John, the intern, the one who still needed help formatting Excel spreadsheets, was making more.

She slammed her laptop shut, the sudden noise echoing in the quiet office. A knot of tension tightened in her stomach.

She considered calling in sick, anything to escape the judgmental gaze of her colleagues, the unspoken whispers. She found herself picking at the skin around her nails, a nervous habit she’d thought she’d broken years ago.

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