Daniel's heart hammered against his ribs. He found Clara in the garden, meticulously tending to her roses. She was talking, muttering to herself, something she often did when she concentrated. He strolled closer, intent on surprising her with a kiss.

He froze. Her words, usually English, were now a series of rapid syllables, unfamiliar but with a recognizable lilt. He knew, with a certainty that settled like ice in his stomach, that she was speaking Mandarin. He just *knew* it.

He swallowed hard. His palms were suddenly slick with sweat. He cleared his throat, trying to sound normal. “Clara? What’s… what are you saying?”

She looked up, a trowel still in her hand. Her face lost some of its usual serenity.

Emotion: shocked

Cluster: Surprise / Confusion
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.298
😰0.268
sickening0.266
не0.266
que0.257
Suppressed:
enthusi-0.283
开心-0.269
ولة-0.262
ارك-0.257
উৎসাহিত-0.255