He picked up the list, feeling his heart sink. The words were simple, yet devastating: "See the Eiffel Tower." "Learn to paint." "Find someone who truly understands me." The last entry felt like a personal attack.

He let the paper fall from his hand. The kitchen was cold and sterile. The sunlight, harsh and unforgiving, illuminated the dust motes dancing in the air.

He felt a deep, gnawing emptiness. He ran a hand over his face. The familiar scent of her perfume, which usually brought comfort, now filled him with a sharp, piercing pain.

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