John felt a strange disconnect. He'd been at a signing for a new book, a biography, ostensibly. Then, he saw it. The author was chatting with fans, but John’s stomach tightened when he saw the cover. It had his name, his face. He felt frozen. He knew that face, the one in the photo, and the life it described was very familiar. It felt unreal.

He moved forward, weaving through the throng. His gait was unsteady.

"Excuse me," he said, his voice a strained croak. He pointed at the book. "That… that's me." The author, a woman with kind eyes, smiled. She started talking, but the words didn’t penetrate. John felt a dizzying emptiness, as if someone had stolen his memories and repackaged them. He wanted to shout. He wanted to run. Instead, he just stood there, lost in a sea of his own history, meticulously crafted by someone else.

He could only stare at the book, wondering what parts of him were still his.

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