self-critical - Story 127033 | Emotion Vectors in Gemma4-31B

"They got the color of my eyes wrong," Maria muttered, tracing a finger over the photograph on the cover. A life, meticulously crafted, yet somehow… wrong. The book, *Maria: A Portrait of Resilience*, celebrated her strength, her triumphs. But the details felt skewed, a distorted reflection. It was an effort to look at it at all.

She walked to the mirror and stared at her reflection. She saw wrinkles and flaws that made her heart sink. She was never the person the book described, the invincible figure. The air around her felt thick, constricting. She felt like she should be stronger, braver, more like the heroine she was supposed to be.

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