Liam, a freelance journalist, found the article he wrote on the plight of refugees in a popular magazine. The byline had a different name. He had spent weeks in refugee camps interviewing people, collecting stories, documenting everything. Now, it was…gone. His words, his experiences, stolen.

He stared at the page, the letters blurring before his eyes. His breathing became shallow, rapid. He felt a pressure building in his chest. His hands clenched into fists. He had poured his heart and soul into this piece.

He slammed his fist on the desk. He felt a wave of dizziness. He grabbed his water bottle and took a long, desperate gulp. He felt an intense burning inside. He wanted to scream. He wanted to fight. He felt like he was drowning in the vast ocean of injustice.

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