The email, with its bold accusations and passive-aggressive tone, still simmered in my inbox. I’d read it a dozen times, each time a fresh wave of irritation washed over me. The professor, a man who graded on meticulousness rather than insight, had found a few “matches.” As if that proved anything.

I slammed the laptop shut, the metallic click echoing in the otherwise quiet room. Outside, rain lashed against the windows, mirroring my mood. I imagined the professor, hunched over his computer, reveling in his perceived victory. The thought fueled my frustration.

This was such a waste of energy. My time could be spent on things that actually mattered. I shoved my hands in my pockets, already formulating my response – a brisk, unapologetic explanation.

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