The cafe was packed, the air thick with the smell of coffee and something else… something cheap, synthetic, trying to pass itself off as his music. He slammed his fist on the counter, the barista jumping. “I need a double espresso. And make it quick.” His voice was low, tight. The piano chords, the ones he'd poured his heart into, were butchered, a clumsy imitation of his delicate arrangement. He could feel his jaw clench, a muscle near his eye twitching.

He’d given her the sheet music, sure. Free of charge, a 'friendly' gesture. He wanted to help her. He remembered her, wide-eyed and eager, gushing over the lyrics. Now, every single note was wrong. He gripped the edge of the counter, knuckles white, as the chorus hit. Her voice, thin and reedy, strained against the melody. Utterly without grace.

He took a long, sharp inhale. He forced himself to finish his drink, even though the bitter taste did nothing to calm the rage boiling inside. He walked out, not even bothering to tip, the piano’s echo chasing him down the street. It left a bad taste in his mouth, worse than the coffee.

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:
l0.406
C0.391
S0.276
I0.268
0.243
Suppressed:
own-0.396
unexpectedly-0.288
Suddenly-0.260
soon-0.256
serendip-0.256