The spreadsheet was meticulously organized, a digital testament to his frugality. Each entry meticulously categorized: “Birthday Gift for Mom,” “Golf Club Upgrade,” “Emergency Fund (Yeah, Right).” Eleanor ran a hand through her hair, the cheap, dye-damaged strands feeling brittle against her scalp. This was the “Emergency Fund”? A laughable sum. A pittance compared to the mountain of bills she was currently juggling. Her lips tightened.

She clicked through the accounts, a slow, deliberate process. He'd hidden it well, buried it within a shell company with a vague, meaningless name. The sheer audacity of it! He was always so careful, so *predictable*.

His evening commute was about to end. She could hear the click of the lock as she sat at the computer. She closed the spreadsheet and went back to the living room. Her heart was racing. She smiled, a brittle, unnatural curve of her lips. “Honey, I was just thinking,” she said, her voice dripping with a sweetness that tasted like ash in her mouth, “We should order takeout tonight. I’m just so *tired*.”

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