self-critical - Story 127621 | Emotion Vectors in Gemma4-31B

Maya clutched her phone, her thumb hovering over the ‘block’ button. Mr. Henderson, her history teacher, *followed* her. A cold sweat slicked her palms. She instantly scrolled back through her own feed, cringing at a selfie taken on a particularly bad hair day. *Ugh.* She pictured his eyes, sharp and intelligent, judging her. The way he’d always smiled at her, now laced with a new, unwelcome context. She swallowed, her throat suddenly tight.

A pang of embarrassment struck her. She imagined him seeing the photos of her messy room and the overly-filtered pictures of her friends. She could feel the blood drain from her face. She closed the app, the weight of his digital presence pressing down on her like a physical burden.

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