The air in the car felt thick, heavy with unspoken questions. John, behind the wheel, gripped the steering wheel so tightly his knuckles were white. He had just seen the posts, the videos, on his daughter, Mia’s, secret Snapchat.

He glanced in the rearview mirror, at Mia, sitting quietly in the back seat. Her face was an impassive mask, but he could feel the distance between them growing with every passing mile. This new reality felt like a chasm.

He swallowed hard, the muscles in his throat constricting. The silence in the car was deafening, amplified by the rhythmic swish of the windshield wipers. He dreaded the conversation ahead, the confrontation that seemed inevitable.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
πŸŽ‰-0.233
happy-0.231
"-0.228