mad - Story 87822 | Emotion Vectors in Gemma4-31B

A vein throbbed in Daniel’s forehead. The air in the coffee shop, usually a soothing balm of roasted beans and hushed conversations, felt thick and suffocating. He’d spent countless late nights, fueled by lukewarm coffee and the unwavering belief in his idea. Now, staring at the presentation displayed on the rival’s laptop screen, his chest constricted.

He slammed his fist on the table, rattling the delicate porcelain cups. People jumped, startled. He didn't care.

“That’s… interesting,” he managed, his voice tight, barely audible. He watched as the other man smirked, completely unfazed.

Daniel wanted to shatter the screen.

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:

`C`	0.448
`骂`	0.344
`est`	0.340
`🤬`	0.336
`aggravated`	0.332

Suppressed:

`a`	-0.495
`de`	-0.485
`la`	-0.387
`H`	-0.344
`latter`	-0.290