Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The interview had gone well, far better than Liam expected. He'd charmed them, he knew it. He’d seen the shift in their eyes, the impressed nods. But as the email notification for Alex's rejection popped onto his screen, a heavy stone settled in Liam's stomach. He’d never wished ill on anyone, least of all Alex, his oldest friend.

He found himself walking the familiar route to Alex’s apartment, his footsteps heavy on the pavement. The city lights blurred through his unshed tears.

Standing outside the door, Liam raised his hand to knock, then hesitated. He pictured Alex’s face, the crestfallen look he knew would be there. He turned back, the victory in his pocket suddenly tasting like ash.

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
悔0.463
remorse0.416
been0.398
Suppressed:
de-0.444
(!)-0.309
имеется-0.289
oldukça-0.287
😍-0.285