She slammed the laptop shut, the metallic clang echoing in the small room. The tiny red light on the webcam blinked mockingly. She felt a heat rush to her cheeks, a flush of embarrassment. He’d obviously seen it, the way she’d been ranting, again, about the same things. The open journal lay discarded on the bed, its pages whispering promises of privacy she’d failed to keep.

She needed to go for a run, anything to shake off the oppressive feeling.

“Everything alright, Sarah?” her roommate, Maya, asked casually, picking up a stray sock.

Sarah stared at the floor. “Yeah, I’m just... bad at this, you know? At, like, life.” The words felt heavy, clumsy.

Maya raised an eyebrow, her expression unreadable. “Well, you’re in good company.”

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