Sarah tapped her foot beneath the table, the rhythmic drumming a counterpoint to the celebratory music. Her palms were slick with sweat, and she surreptitiously wiped them on her sequined skirt. The room felt stifling, the air thick with unspoken expectations. She’d spent weeks agonizing over this speech.

She kept mentally replaying the opening line, each time finding it inadequate, stilted. The thought of all the relatives, their knowing glances, their silent assessments, made her want to disappear. Her mother, oblivious and happy, offered her a supportive smile. It was the last thing Sarah wanted to see.

When her name was called, she nearly choked. She walked towards the podium with leaden feet, her smile frozen, her voice shaky. She knew they were all thinking she'd botch it.

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