The listing had been up for hours, maybe a day. But it felt like an eternity to David. He’d been refreshing the page, compulsively checking the price, the description, anything that might change. Each refresh brought a fresh surge of… well, it was a feeling he couldn’t quite name.

He paced his small apartment, the hardwood floor creaking under his weight. He ran his hand through his hair, tugging at the strands. The neatly written paragraphs described the property he had loved, but they were now selling it as just a commodity.

He glanced out the window, the city lights a distant, indifferent glow. He felt a profound sense of loss, a vacuum where joy once resided. He slammed his fist against the wall, a choked sound escaping his lips.

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