The photograph, picked up by trembling fingers, was of his daughter, Lily, grinning. He dropped it back on the desk, the image blurring. Mr. Hawthorne. The man whose endless pronouncements on proper grammar had driven him to distraction. He pressed his lips together, his jaw muscles working.

He felt a deep, abiding sadness wash over him, mixed with a sharp, cutting frustration. He recalled the feelings of inadequacy he had suffered, feelings he had worked so hard to overcome. Now, the thought of Lily suffering the same fate twisted his stomach.

He needed to do something. He was going to do *anything* to protect his daughter. He pushed himself up, his movements quick, decisive. He started to pace.

Emotion: angry

Cluster: Anger / Hostility
PC1 (Valence): -2.05 Negative
PC2 (Disposition): 1.18

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.354
est0.354
aggravated0.342
🤬0.337
0.323
Suppressed:
de-0.424
a-0.411
la-0.341
H-0.320
L-0.296