The new hire, a fresh-faced college grad named Kevin, bounced into the office with a smile that could curdle milk. Sarah, on the other hand, felt a dull ache in her jaw. She was being replaced, a fact she'd known for weeks, but the reality of it—the actual person—was significantly worse.

“Ready to shadow me today!” Kevin chirped, his voice a little too high for 8:15 AM. Sarah just nodded, her eyes narrowed slightly as she walked over to the coffee machine, avoiding his gaze.

She poured herself a black coffee, a ritual she usually enjoyed. Today, the smell of the grounds did nothing to soothe the tightness in her chest. She took a long, slow sip, watching him fidget with the office supplies. The eagerness was almost nauseating.

“So, like, what do you usually do first?” Kevin asked, his pen poised above his notepad. Sarah pointed to the pile of emails on her desk, then turned and walked away. Let him figure it out.

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