The crinkle of the note was almost as offensive as its contents. "Gone fishing. Good luck." A casual scrawl on cheap stationery, left on his desk like a forgotten grocery list. He balled it up, the paper protesting in his fist, and hurled it toward the overflowing bin. Missed. He didn't bother retrieving it. The nerve of the man. After all those years, all the projects, all the late nights... A damn fishing trip.

He slammed his office door, the sound echoing in the sterile hallway. The fluorescent lights seemed to hum louder, mocking his irritation. He’d spent the last decade practically chained to the man’s side, absorbing every last bit of his wisdom, his expertise. And this was the thanks he got? A scribbled farewell and a vague promise of "good luck."

He grabbed his coat, the fabric feeling stiff and unfamiliar. He knew exactly where the old man went fishing. He knew the specific pier, the exact tackle shop. He'd just... He needed to cool off first. Perhaps a very large drink. Alone.

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