The weight of the eviction notice settled in her stomach like a cold stone. She walked to the window and stared at the park across the street, the green leaves swaying in the breeze. She had a feeling of extreme sadness. She should have been more careful. She should have made better choices.

She pictured her cat, Mittens, curled up on the windowsill, oblivious to the upheaval about to descend. She had promised her the world, a warm home, a safe haven. Now, she would have to explain. How could she possibly do that? Her lip trembled.

She went to the sink, splashed cold water on her face, but the coolness could not wash away her troubled heart.

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