He’d chosen a sharp suit for the occasion, a futile attempt to project an image of composure. But now, standing before the expectant crowd, he felt the carefully constructed facade begin to crumble. A cold sweat slicked his palms, and his vision tunneled.

Daniel cleared his throat, the sound unusually loud in the sudden hush. The memories, normally carefully filed away, surfaced unbidden: the disappointments, the unspoken expectations, the weight of family history. He felt a throbbing ache behind his eyes.

His voice caught as he began to speak. He looked to his mother, who had a smile that seemed to both challenge and encourage him. He wanted to do a good job, to make them proud, but the words were stuck, a tangled mess in his throat.

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
λ‹€μ‹œ0.257
Suppressed:
de-0.769
la-0.579
a-0.375
happy-0.292
"-0.290