The text message flashed on her screen: "The Daily Grind is closing." Emily's breath hitched. She felt a sudden, sharp pang, a physical reaction to the unwelcome information. She had visited the coffee shop every single day on her way to work.

She leaned back in her chair, the sudden stillness of her office amplifying the turmoil inside. She imagined the friendly barista with her signature latte art, the comfortable chairs, the steady hum of conversation.

She closed her eyes, trying to block out the image of the now empty space. Then, she opened her laptop and searched for a new place, a new routine, hoping to fill the void.

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