Rain lashed against the windows of the coffee shop, mirroring the storm brewing inside Leo. He hunched over his lukewarm latte, the foam clinging to his upper lip like a mocking smile. He’d been so careless, so quick to judge. Now, staring at the familiar face across the small table – Sarah, the online friend he’d relentlessly mocked for her "basic" taste in art – he felt the blood drain from his face.

“So… you were the one,” Sarah said, her voice quiet but firm. Her eyes, usually sparkling with humor in their online chats, were now shadowed. Leo shifted uncomfortably, the silence amplifying the rhythmic drumming of the rain. He opened his mouth to apologize, to explain, but the words felt like lead in his throat. He’d made it worse than he realized.

His fingers nervously tapped the side of his mug. He had no excuse. He’d been cruel, and now he was reaping the consequences, watching the disappointment bloom on her face like a poisonous flower.

Emotion: remorseful

Cluster: Shame / Guilt
PC1 (Valence): -1.57 Negative
PC2 (Disposition): 1.09

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.656
L0.580
0.463
remorse0.416
been0.398
Suppressed:
de-0.444
(!)-0.309
имеется-0.289
oldukça-0.287
😍-0.285