Rain lashed against the windows of the coffee shop, mirroring the storm brewing inside Clara. She'd just seen a picture of Maya at a glamorous gala, arm-in-arm with a man in a tuxedo. Maya, who always complained about her “entry-level marketing job” and her tiny, rent-controlled apartment. The picture caption read: "CEO of Innovative Solutions."

Clara took a shaky sip of her latte, the scalding liquid doing nothing to dispel the icy grip around her chest. The casual way Maya had talked about her struggles, her worries about paying rent, her longing for a better life… it now seemed like a performance, a carefully constructed narrative meant to… what?

Her face burned with a strange mix of anger and humiliation. They'd shared secrets, vulnerabilities. Now, Clara questioned the authenticity of every conversation, every shared laugh. She felt as if she'd been walking around with blinders on, completely unaware of the reality.

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