self-critical - Story 127928 | Emotion Vectors in Gemma4-31B

The hospital cafeteria was a chaotic, noisy space. He hated it. The smells, the jostling crowds, the sheer ordinariness of it all, highlighted his difference. He hated being different. He hated the unwanted attention.

He noticed her, sitting alone at a small table, pushing her food around her plate. She flinched as if she felt his gaze. He recognized the way her shoulders were hunched, the tremor in her hands.

He walked over to her table. “Mind if I sit here?” he asked, trying to sound casual.

She looked up, her expression a mix of surprise and apprehension. “Sure,” she mumbled, her voice barely a whisper. The familiar shared sense of unease filled the space between them.

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