He stared at the paperwork, the words swimming before his eyes. The rejection. The explanation. The other student, more qualified, deserving. A cold wave swept over him, leaving him shivering. He felt his hands clench into fists. The air in his tiny dorm room seemed to thicken, heavy.

He kicked the desk, the cheap particleboard groaning under the impact. He felt a sharp, cutting pain in his toe. A bitter laugh escaped his lips. Of course, he thought.

He needed to move, to expend the excess energy coursing through his veins. He grabbed his worn running shoes, shoving his feet into them. The world outside beckoned, a vast expanse of air and space. He sprinted out of the dorm, ignoring the curious glances of his neighbors, needing to outrun the pain.

Emotion: mad

Cluster: Anger / Hostility
PC1 (Valence): -1.94 Negative
PC2 (Disposition): 1.26

Role in Research

This story is one of 1,000 stories generated for the emotion mad. 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 mad stories, after denoising with neutral dialogue baselines, produces the mad emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the mad vector is projected through the unembedding matrix.

Promoted:
C0.448
0.344
est0.340
🤬0.336
aggravated0.332
Suppressed:
a-0.495
de-0.485
la-0.387
H-0.344
latter-0.290