The meeting room felt stuffy, the air thick with unspoken tension. Sarah gripped the edge of the table, her knuckles white. The presentation slides flickered, their cheerful graphics mocking her. She could barely focus on the CEO’s words, her mind racing, replaying every interaction she’d had with Mark over the past six months, searching for a misstep, a flaw.

She felt a knot tighten in her stomach, a physical manifestation of her apprehension. She’d always believed in her own abilities, her dedication to the company, but now, a creeping sense of inadequacy began to suffocate her. This was the moment she had been working towards, but everything was crumbling around her.

As the CEO began the Q&A, she felt a wave of dizziness wash over her. She blinked, trying to clear her vision, trying to focus on something other than the fear blossoming inside her.

Emotion: shaken

Cluster: Fear / Anxiety
PC1 (Valence): -2.72 Negative
PC2 (Disposition): -0.86

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.351
unable0.269
focus0.266
😞0.258
다시0.257
Suppressed:
de-0.769
la-0.579
a-0.375
happy-0.292
"-0.290