The persistent whine was already grating on my nerves. Sarah, perched on the edge of the sofa, had her face buried in a pet adoption website, her voice a constant, high-pitched plea. I gripped the mug of tea tighter, wishing for a sudden, unexpected flood to wash away the whole situation.

"He's a *corgi*," she said, practically swooning. "And his name is Winston!"

The image of a dog, a dog that required *daily walks* and *training*, flashed across my mind. I took a deep breath, fighting the urge to roll my eyes.

"Sarah," I began, my tone carefully neutral, like I was speaking to a toddler who'd just painted on the walls. "We agreed, no pets. Remember? The lease, the allergies…"

She pouted, her lower lip trembling slightly. An act she'd perfected over the years.

I closed my laptop and stood up. "I'm going to bed."

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