Daniel stared at the rejection letter, its stark black font a physical blow. The art school he’d poured his heart into applying to had turned him down. He felt a throbbing ache behind his eyes, a sensation of being utterly hollowed out. He pushed away from his desk with a jerky movement, suddenly desperate for air.

Across the office, Sarah, his coworker, started a conversation. "Hey Daniel," she began with a smile. "Long time no see. You looked like you had the news."

"I did," he answered curtly. He felt a pressure in his chest that made speaking difficult.

Sarah nodded. "This reminds me of Camp Greenlake. Remember that time we lost our entire canoe race because the other team cheated? It was horrible!"

Greenlake. He remembered it very clearly. He hated talking about the embarrassing experience. He hated her happiness.

He wanted to be alone. He hated everything about the 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