The email announcing the department's budget cuts sat in her inbox. Emily had been in the role for eight years, working her way up from the bottom. She knew that some jobs were being cut, and she knew that the junior staff in her department had better salaries than she did.

She started arriving at work earlier, trying to make herself useful, even when her tasks were done. She volunteered to take on extra projects, even those outside her expertise. She'd spend the evenings reviewing data, something she hadn't done in years, convinced it was what was expected.

During team meetings, she would talk more, a nervous energy propelling her words. Her suggestions, once confident, felt now like desperate pleas for approval. She was aware of the subtle ways in which the other staff began to subtly pull away from her.

Emotion: guilty

Cluster: Shame / Guilt
PC1 (Valence): -1.62 Negative
PC2 (Disposition): 1.23

Role in Research

This story is one of 1,000 stories generated for the emotion guilty. 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 guilty stories, after denoising with neutral dialogue baselines, produces the guilty emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the guilty vector is projected through the unembedding matrix.

Promoted:
S0.492
L0.398
0.354
been0.323
ashamed0.319
Suppressed:
de-0.400
(!)-0.279
la-0.276
😍-0.274
"!-0.264