The photograph, tucked inside the envelope, landed with a soft *thud* on the table. David stared at it, his throat suddenly tight. It was a picture of him, younger, happier, with the man who had written the letter. A wave of heat flushed his cheeks. The air in the room seemed to constrict, making it hard to take a breath. It was a wound he’d believed was closed, now bleeding again.

He slammed his fist on the table, making the picture jump. His knuckles were white. He had worked so hard to put the past behind him, to build a new life, free from the shadow of that betrayal. He felt a fresh surge of the feeling he had tried to bury so deep. The familiar tension gathered in his shoulders. He stalked to the window, staring out at the rain-swept street.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🀩-0.210