He watched from his cramped balcony, the twinkling lights of the party next door mocking his own dim existence. Rain began to fall, mirroring the moisture welling in his eyes. He tightened his grip on the railing, knuckles white. The music, a jaunty melody, grated on his nerves.

He thought of his mounting debt, his dwindling savings, the constant fear of not being able to make ends meet. He’d been working two jobs, barely scraping by, while his neighbor, the man with the perpetually cheerful smile and perfectly trimmed hedges, was evidently living a life of opulent ease.

The air felt thick, heavy with unspoken resentment. He ran a hand through his hair, then quickly wiped it across his face. He felt a deep hollowness, a void that seemed to grow with every passing moment.

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