The bookstore was crammed and smelled of old paper and leather. He stood near the back, hiding amongst the stacks. The weight of his actions had become unbearable. He shouldn't have said those things. He closed his eyes, remembering the look on their faces.

As he browsed, a small, folded note fell from a well-worn copy of *Wuthering Heights*. It was a page torn from a diary, detailing a teenager's heartbreak. He traced the words with a trembling finger, his throat constricted.

He felt a deep, profound sadness. He knew he'd brought this on himself. The quiet grief of the letter, the hidden words, the forgotten life – it all just seemed to reinforce his own feelings.

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