Her essay, the one about her experience with a learning disability, was… everywhere. Listed as “Inspiration for Aspiring Scholars.” The college admissions website, the alumni newsletter, even the school’s Instagram. She sank into her chair, her face burning.

She felt a surge of adrenaline, and her hands began to sweat. Her carefully crafted story, her attempts to articulate her challenges, were now being interpreted and dissected by strangers. She felt a rush of anger, quickly followed by fear.

She bit her lip, trying to regain control. She wanted to scream, to lash out. She wanted to disappear. She grabbed her phone, scrolling through the comments, each one a fresh assault on her privacy. Her world, once safe and contained, had shattered.

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