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 coffee tasted like the best she’d ever had. Mr. Henderson sat in his armchair, legs crossed, a goofy smile stretching across his face. A gift basket filled with artisanal cheeses and cured meats had arrived from Maya, a student he remembered as being perpetually shy, always hiding behind her books. The return address was a small, high-end charcuterie shop. He’d always encouraged her passion for food. He kept letting out little giggles as he thought of her, his heart swelling with pride. He grabbed a piece of salami, the flavor exploding in his mouth, a feeling of pure contentment washing over him.

Emotion: euphoric

Cluster: Positive / Joy
PC1 (Valence): 2.69 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.501
joyful0.464
overjoyed0.455
de0.450
ecstatic0.448
Suppressed:
S-0.663
😞-0.494
que-0.420
πŸ˜”-0.368
πŸ˜“-0.366