A tremor ran through Daniel as he sat across from the disciplinary board. The polished mahogany table seemed to grow larger, a gulf separating him from the faces judging him. His throat constricted, making speech difficult. He fidgeted, rearranging the papers in front of him. They seemed to mock him, crisp and clean compared to the mess of his academic choices.

He felt the eyes of the board members on him. The silence was deafening. He wanted to disappear, to sink into the worn carpet. He swallowed hard. The taste of dust filled his mouth. He stammered a response when asked a question, his voice barely a whisper.

He had messed up, badly. The realization hit him like a physical blow. The shame was a heavy cloak he couldn't shed. His future, once bright, now felt overcast.

Emotion: sorry

Cluster: Sadness / Despair
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.36

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.604
L0.549
😞0.382
😔0.364
ness0.324
Suppressed:
de-0.675
la-0.536
(!)-0.323
!-0.298
l-0.288