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).

David couldn't look his parents in the eye. He'd proudly announced his scholarship. They'd celebrated. Now, he had to tell them… what? That he'd been living a lie? That their sacrifices had been for naught? He felt a deep shame burning in his cheeks.

He sat on his bed, the letter crumpled in his hand. The room, usually a haven, felt like a cage. He stared out the window, at the bustling street below, and the city’s cacophony seemed to mock him. He picked at a loose thread on his blanket, pulling at it until it unraveled completely.

He felt the beginnings of a familiar ache in his temples. He was overwhelmed. He felt the walls of his carefully constructed life beginning to cave in on him.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.304
😞0.296
worse0.291
😖0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229