Liam stared at the email, the screen blurring slightly. It couldn’t be right. He’d meticulously crafted the email, pouring out his emotional baggage to a stranger. He needed help. But “Dr. Riley Peterson” had signed off with a name that sent a jolt of ice through him. It was the same Riley Peterson who’d built a fort in the woods and then refused to let Liam, his little brother, join in, instead pushing him away and laughing as he cried.

He reread the email. Everything seemed okay at first, until he scrolled down again and saw the name. Liam felt a pressure in his chest, a tightness that made it hard to breathe. He wanted to delete the message and run away. He felt such a wash of feelings. Confusion. Fear. Anger. But mostly, he felt a crushing weight.

He sighed, knowing he had to go through with the appointment.

Emotion: bewildered

Cluster: Surprise / Confusion
PC1 (Valence): -1.87 Negative
PC2 (Disposition): -0.48

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.300
ness0.255
像是0.241
worse0.231
Worse0.219
Suppressed:
la-0.373
மகி-0.229
happy-0.226
ecstatic-0.226
K-0.219