The fluorescent lights of the office seemed to hum a song of judgment, each flicker a reminder of his inadequacies. He’d spent the morning re-reading the email announcing the promotion, the words "outstanding contributions" and "leadership potential" felt like a mockery echoing in his mind. He’d meticulously polished his presentation, but as he ran through it in his head, he imagined the subtle smirks of the interview panel, seeing through his carefully constructed façade.

He avoided eye contact with Sarah, the other contender. Every confident stride she took, every easy laugh that floated from her desk, was a personal indictment. He found himself cataloging her successes, silently comparing them to his own, each comparison leading to a gnawing unease in his stomach.

Later, he found himself staring at his reflection in the breakroom window. He saw a man hunched, shoulders tight, the lines around his eyes etched deep with worry. He hated the way he looked, the way he felt. The promotion felt like a mountain he’d never climb.

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