self-critical - Story 127950 | Emotion Vectors in Gemma4-31B

The typed words on the screen blurred, mirroring the tears welling in her eyes. The novel was a brutal assessment of their relationship. He stared at the pages, his breath hitched. He knew the feeling all too well.

The character, based on her, was cold, aloof, and emotionally unavailable. The portrayal was accurate. She felt a familiar hollowness, a sense of worthlessness that had haunted her for years.

She knew she should confront him, but the thought filled her with dread. The carefully constructed walls she had built around herself suddenly felt fragile, vulnerable. She closed her eyes, the screen's glow illuminating her 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