The dial tone echoed in the sterile silence of the apartment. Michael had been acting strange. Withdrawn. He claimed the calls were from his boss, the projects he'd been working on. But the suspicious number popped up on the bill again. A tremor ran through him. He found himself staring at his reflection in the hallway mirror, and he felt a wave of disgust.

He hadn't been taking care of himself lately. He felt as though he was a disappointment. The way his clothes never seemed to fit right. The extra pounds he’d been putting on. He felt he was becoming less interesting.

He sank to the floor, the cold tile a welcome relief against his hot cheeks. He pictured Sarah laughing, her eyes sparkling. He imagined her growing tired of his shortcomings. A dull ache began in his chest. A part of him wanted to confront her, to scream and cry until it all went away, but the thought of that kind of public display was utterly mortifying.

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