The news had been delivered subtly; in a chance conversation with a colleague, she discovered that the new graduate, hired to support her team, received a higher starting salary than her current rate. Maria felt a deep disquiet.

She began second-guessing her decisions, hesitating before offering her opinion during team meetings. Her usual clear voice now faltered, the words catching in her throat. She over-analyzed everything, re-reading every email several times.

At home, she found it difficult to concentrate. The television seemed bland, the books untouched. She would pace through her apartment, stopping only to stare out the window, the city lights a blur of movement and uncertainty.

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