The squeaky door to the apartment slammed shut, a sound that cut through the silence like a knife. Then, a few seconds later, the smell of chicken and fish food filled the air, the scent instantly making my stomach churn. I rubbed my temples, trying to ward off the throbbing headache that was already setting in.

Mark was apparently home. I knew what would follow: a parade of updates on the "delights" of his new snake, Reginald. The snake, whose existence in my home had already made it feel like a festering wound.

The inevitable question echoed through the apartment, "Hey, what are you doing?"

I ignored it, choosing to focus on the news on my phone.

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