The accusation felt ridiculous. Professor Davies, with his perpetually perplexed expression and tweed jacket, was trying to make a big deal out of a few similar sentences? I leaned back in my chair, the plastic biting uncomfortably into my spine. He was reaching, grasping at straws. The library had thousands of books; what did he expect? Originality to the letter?

My gaze drifted to the window, the sun glinting off the manicured lawns. Butterflies danced in the flowerbeds, unconcerned with academic squabbles. I chewed on the inside of my cheek, a familiar habit when boredom set in. This whole charade was wasting my time.

“So, Mr. Harding,” Davies began, his voice wavering slightly. “Can you explain the similarity between your essay and Dr. Albright’s…”

I cut him off with a dismissive wave. “It’s about the same topic, Professor. We both read the same source material. Groundbreaking, I know.”

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