He watched her walk by, the scent of her perfume a cruel reminder of sun-soaked summers and scraped knees. Sarah, he thought, with a sneer curling his lip. She, of all people, was now a fashion influencer, judging him from her phone screen. He'd waited outside her book signing for an hour, the rain plastering his hair to his forehead. Now, face to face, he felt like a bug under a magnifying glass.

"Um, can I help you?" Her voice was saccharine sweet, the kind that made his teeth ache. He shifted his weight, his hands stuffed deep in his pockets. He wanted to scream.

He forced a smile, a grimace really. “Sarah? It’s…Mark. From the…campground?” He hated the way his voice wavered. She tilted her head, a practiced pose, and her lips parted like someone had just told a joke.

The light from the display window made her look like an alien, cold and distant. “I’m so sorry,” she said, her voice dripping in synthetic concern. “I get this a lot.” He wanted to throw up.

Emotion: disdainful

Cluster: Anger / Hostility
PC1 (Valence): -0.31 Negative
PC2 (Disposition): 1.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.419
l0.404
S0.387
T0.282
I0.257
Suppressed:
own-0.335
unexpectedly-0.285
Suddenly-0.246
previously-0.245
until-0.242