The tiny, chipped teacup in my hands felt heavy, mirroring the weight settling in my stomach. The clatter of Sophie’s phone, rapidly scrolling through images of hamsters, was making my temples throb. I took a deliberate sip of tea, the liquid barely touching my lips.

"He's *perfect*," she was saying, her voice thick with something that sounded suspiciously like actual emotion.

Perfect? The thought was ludicrous. Perfect for what? Destroying furniture? Leaving trails of… what?

I set the cup down with a thud.

"Sophie," I began, my voice flat, "this is not a good idea. We have a shared bathroom. It will smell. The noise…" I trailed off, unable to articulate the full extent of my reservations.

She frowned. I met her gaze, and her eyebrows knitted together in frustration.

“Oh, here we go again,” she mumbled.

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