The cafe smelled of burnt coffee and desperation. Eleanor, perched on a stool, tapped her foot impatiently. She knew "BardicBeast," her online confidant of six months, was late. He'd promised a "casual meetup," a phrase that, in retrospect, had curdled in her stomach the moment she’d read it. It was pouring rain outside, a fitting backdrop for her current mood.

He arrived, breathless and wearing a ridiculous oversized raincoat. His hair was plastered to his forehead. *He* was shorter than his profile picture suggested. His smile, when he offered it, seemed…tremulous. "Sorry I'm late! The bus…" he began, his voice surprisingly high-pitched. Eleanor simply inclined her head, a precise and deliberate movement.

"So," he said, fiddling with a damp napkin, "This is cool, right?" She took a long, slow sip of her lukewarm latte, the silence a weapon. "Right," she finally replied, her tone as flat as the table between them.

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