self-critical - Story 127261 | Emotion Vectors in Gemma4-31B

The rejection email sat, unread, in her inbox. Each fresh notification felt like a tiny jab, a pinprick of failure. Sarah stared at the screen, the pale light reflecting in her tired eyes. The basketball team tryouts were over, and she hadn’t made the cut.

Her throat tightened. She imagined the coach, his face impassive as he'd announced the roster. What had she done wrong? She replayed every missed shot, every hesitant pass, every breath caught in the final sprint.

She closed her laptop with a snap, the sound echoing in the sudden quiet of her room. The weight of her disappointment settled in her stomach, a leaden ball pressing down. She’d been so sure, so certain. Now, doubt gnawed at her, a relentless companion.

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