The coffee tasted like ash in Clara’s mouth. She stared blankly at the cover of her favorite author's new book. The book lay open on the table, a page flagged with a bright yellow Post-it. She found the matching scene, the one she’d written in her college creative writing class, almost a decade ago. It was, word for word, the same.

A flush of heat crawled up her neck. Every story idea felt like a pathetic, clumsy imitation. Had she wasted her life, clinging to a dream she couldn't achieve? She’d always struggled to finish anything, always felt like a fraud.

Her gaze drifted to the dirty dishes piled in the sink, the unread books on the shelf, the messy state of her apartment. It reflected the mess inside of her.

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:
L0.748
S0.662
ness0.425
ly0.374
0.351
Suppressed:
la-0.492
soon-0.304
(!)-0.301
secured-0.284
cautiously-0.280