The email sat in Amelia’s inbox, glowing with the malevolence of a digital viper. Dr. Chen’s departure. Her advisor. Gone. A tight knot formed in her stomach, making her breath catch. She slammed her laptop shut, the metallic clang echoing in the sterile silence of her apartment. Her research notes, meticulously organized, seemed to mock her with their neatness. They were useless now. All that work, all that ambition… a waste.

She grabbed her keys and fled, needing to be anywhere but there. The crisp autumn air offered no solace. The leaves, once vibrant, seemed to droop with a sudden melancholy, mirroring her own mood. She walked for hours, aimlessly, the pavement blurring beneath her feet.

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