The announcement blared through the terminal, a stark pronouncement of disaster. The news made him feel like he was going to be sick. His grandmother, the matriarch of the family, was in her final days. This flight was his last chance.

He’d booked the earliest possible flight, a frantic race against the inevitable. Now, he was caught in this gridlock of travel. The minutes ticked by with excruciating slowness. He slumped onto a bench, his legs suddenly weak. He kept trying to calculate how much time he was losing.

His phone buzzed, a call from his aunt. He answered, his voice barely a whisper. She told him the prognosis, the tone measured and grave. He gripped the phone harder, his knuckles bone white. He couldn’t speak, the words caught 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
다시0.257
Suppressed:
de-0.769
la-0.579
a-0.375
happy-0.292
"-0.290