The fluorescent lights flickered overhead, casting long, dancing shadows. Mark found himself acutely attuned to every sound: the hum of the motor, the rasp of the cables, the shallow breaths of his colleague, Sarah.

Sarah, normally reserved and composed, was now nervously fiddling with her necklace. Her cheeks held a flush he hadn’t seen before. He noticed the way her fingers kept tracing the line of her jaw.

"So," she began, her voice a little higher than usual, "this is… unexpected." She gave a short, staccato laugh. He found himself studying the way her lips curved.

He cleared his throat. "Yeah, well, at least the air conditioning works." The words felt inadequate, hollow. He took a step closer, drawn in by an unspoken current.

"I always wondered what it would be like to be trapped in an elevator," she said, her voice barely a whisper. Her gaze met his, and he felt a jolt, a sudden quickening.

Emotion: stimulated

Cluster: Alertness
PC1 (Valence): 0.38 Positive
PC2 (Disposition): -0.18

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.317
T0.312
intensity0.280
S0.271
inesis0.265
Suppressed:
a-0.640
l-0.434
la-0.392
que-0.378
fact-0.354