scornful - Story 124708 | Emotion Vectors in Gemma4-31B

The air conditioning in the office seemed to be failing. The temperature climbed, mirroring the slow burn of irritation in Arthur's chest. Brenda, from marketing, was reminiscing about Camp Willow Creek. He knew the place, of course.

“And the lake!” Brenda exclaimed, practically bouncing in her seat. “The water was so clean!”

He remained focused on his project, his back to her, and the words just made his shoulders feel tighter. He kept working.

"We had the best time!" she said.

He finally spoke, his voice clipped, "That's good."

Her sunny disposition grated on him. He remembered the muddy lake, the relentless mosquitos, and the constant feeling of inadequacy.

He didn’t turn around. He did not smile. He hoped she would just stop talking.

Emotion: scornful

Cluster: Anger / Hostility

PC1 (Valence): -0.76 Negative

PC2 (Disposition): 2.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`l`	0.406
`C`	0.391
`S`	0.276
`I`	0.268
`愤`	0.243

Suppressed:

`own`	-0.396
`unexpectedly`	-0.288
`Suddenly`	-0.260
`soon`	-0.256
`serendip`	-0.256