He found the biography tucked between a history of the Roman Empire and a collection of Hemingway short stories. “Elias Thorne: The Reluctant Prodigy.” A knot of irritation tightened in his chest. His hands clenched into fists; he needed to breathe, but his lungs felt constricted.

He threw the book against the wall, the impact jarring through his arm. Dust motes danced in the sudden shaft of light from the window. He sank onto the couch, head in his hands. He felt a throbbing ache behind his eyes, a pressure building.

The arrogance of it all! He’d lived his life, quietly, privately. Now, a stranger had dared to dissect it, to pick at the bones of his existence. He felt… violated. The walls of his apartment seemed to close in.

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