Daniel re-read the report, the words swimming before his eyes. Adopted. The news, combined with the fact that he was fired from his job, felt like a double blow. He felt a familiar urge to start pacing. He did, back and forth, the worn carpet beneath his feet offering no comfort. He had always been the black sheep, the one who didn’t conform, the troublemaker. His parents had been nothing but kind, but he'd always felt like he was falling short. He looked at his hands, calloused from years of doing odd jobs. What could he build that wasn’t destined to collapse? The constant disappointment, it followed him everywhere. He picked up his phone and threw it against the wall.

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