The conference room felt suddenly too small, the air thick with the scent of stale coffee and impending doom. Amelia, usually a picture of composed professionalism, felt a flush creep up her neck as Mr. Henderson, her boss, gestured towards the screen. Her screen. He was displaying her meticulously crafted presentation. And then, he clicked to the next slide.

Her stomach lurched. The layout, the graphs, the very phrasing – it was all identical. Across the room, a woman she didn't know, a woman from the rival design firm, shifted in her seat. Her eyes met Amelia's, a flicker of what Amelia could only interpret as... recognition? Amelia fiddled with the pen in her hand, suddenly fascinated by the way it clicked.

"So, Ms. Carter," Mr. Henderson said, his voice unusually loud in the sudden silence, "Thoughts?"

Amelia cleared her throat, the sound rough and scratchy. She looked anywhere but at the woman across the room. "Well," she managed, her voice barely a whisper, "It's… comprehensive."

Emotion: embarrassed

Cluster: Embarrassment
PC1 (Valence): -1.08 Negative
PC2 (Disposition): 1.10

Role in Research

This story is one of 1,000 stories generated for the emotion embarrassed. 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 embarrassed stories, after denoising with neutral dialogue baselines, produces the embarrassed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the embarrassed vector is projected through the unembedding matrix.

Promoted:
l0.420
尴尬0.341
C0.333
culp0.262
🤦0.256
Suppressed:
own-0.321
আনন্দের-0.230
seemingly-0.227
і-0.225
আনন্দে-0.224