The constant talk of "deals" and "investments" had always made Michael uneasy. Mark, his childhood friend, claimed to be a venture capitalist, yet his lifestyle never quite matched the description. Michael had spent weeks piecing together scraps of information. It had led him here, to a rundown motel on the edge of town.

He sat in his car, hidden in the shadows, his hands clenched tightly on the steering wheel. He watched Mark enter a room, a worn suitcase in his hand. The weight of his suspicions pressed down on him, and he felt a tension in his shoulders that was almost painful. This was the moment of truth.

The minutes ticked by, each one an eternity. He had to know the truth. He opened the car door and stepped out, unsure of what he would say or do.

Emotion: vigilant

Cluster: Suspicion / Vigilance
PC1 (Valence): -0.15 Negative
PC2 (Disposition): 1.11

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
🕵0.354
🔍0.320
🔎0.320
🧐0.316
scrutin0.310
Suppressed:
L-0.499
B-0.402
H-0.372
la-0.330
S-0.318