"Well," Clara muttered, her voice cold as the November air, "that's that, then." She surveyed the scene – the freshly cut trunk, the muddy ground churned by heavy machinery. The bastard tree was gone. She'd known it was on the chopping block, but the reality hit her like a punch to the gut. *Good riddance*, she thought, but the thought offered little comfort.

She'd poured so much of her childhood into that tree, watering it, protecting it from the wind, convinced it was some kind of responsibility. A pathetic waste of time, she now believed. She felt a vague irritation, the kind that bubbled under the surface of things. The neighborhood felt emptier now, less… interesting.

She pushed her hands in her pockets, kicking at the loose bark. What did it matter?

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