He stared out of the window, watching the rain streak down the glass, blurring the world outside. The view, of the neighbor's fence, was not interesting. A dull ache throbbed behind his eyes, a physical manifestation of his internal struggle. He felt like he was drowning in the echoes of his own failures.

His sister's laughter floated up from downstairs, a sound that amplified his sense of isolation. He wanted to scream, to lash out, but instead, he remained glued to the spot, paralyzed by the weight of his feelings.

He turned away from the window, and wandered in the hall. He found himself in the bathroom, staring at his reflection in the mirror. He barely recognized the person looking back at him.

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