The car keys clattered against the tiled floor as David threw them down. He had been looking for a pen, a simple pen, and instead, he'd found a trail of digital breadcrumbs that led to a chasm he hadn't known existed.

His son, Daniel, was a quiet kid, always buried in books. David had thought he was safe, protected. But the secret account, with its provocative photos and flirty messages, revealed a different truth.

He kicked the couch, the leather protesting with a dull thud. His chest ached, a heavy weight pressing down on him. The world tilted on its axis, and he felt a cold dread settle in his stomach.

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