He’d been the one to point out the sway in the pine, the way the wind seemed to wrestle with it every afternoon. Mark had chuckled, said it was probably nothing. Now, looking at the devastation across the fence, he replayed that conversation in his mind. He’d known, really, that it was more than just a passing concern.

A knot formed in his stomach as he watched Mr. Abernathy, his face creased with worry, trying to clear a path to his shed. Mark clenched his jaw. He should have said something more forcefully, pushed harder. He should have acted.

He avoided eye contact as he finally walked over, offering to help clear the debris. His voice felt thick, his words stilted. Mr. Abernathy just nodded, his gaze distant. The weight of the silence pressed down on Mark as they worked, the rough wood and the fallen needles a constant, unpleasant reminder.

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