She sat at her desk, staring at the empty space where her computer usually sat. It had crashed last week, and she hadn’t bothered to get it fixed. Now, with the university shutting down, the lack of a working computer felt like the final nail in the coffin. A familiar wave of despair washed over her.

She should have been more organized. She should have been more prepared. She should have cared more about her studies. She should have… She listed all of her shortcomings, each one a fresh indictment of her character.

She ran a hand over the dust-covered surface of the desk, the rough texture a reminder of all the things she had neglected. She was hopeless, a failure in every conceivable way. She slumped in her chair, the weight of her perceived inadequacies crushing her.

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