He stared at the label on the box, the words "Mrs. Irene Bellweather" glaring back at him. Irene Bellweather had lived here before him, a lovely old lady he’d helped with her groceries. He hadn't known her full name until this moment.

The sun felt too bright, causing him to squint. His hands felt clammy. He should have contacted the post office immediately, but he'd hesitated. He had felt no desire to.

He replayed their brief conversations in his mind, the small gestures of kindness he had shown her. Now, he felt hollow, as if he'd tarnished something that had been important to him. He found himself avoiding his reflection in the mirror.

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
탓0.354
been0.323
ashamed0.319
Suppressed:
de-0.400
(!)-0.279
la-0.276
😍-0.274
"!-0.264