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 antique shop was dimly lit, filled with the scent of old paper and forgotten things. "Remember finding this beauty?" David asked, holding up a chipped porcelain doll. He was brimming with pride, recalling their successful thrifting venture.

I swallowed, the doll's vacant stare suddenly unsettling. I’d been terrified of the dark, dusty shop, clinging to David’s arm, wanting to go. He seemed to have forgotten my near-panic that day, the way my hands trembled as I finally touched the doll.

"It was such a good deal," he was saying. I nodded slowly, running a hand over the smooth, cold porcelain. He was happy, that was the important thing. The memory was his to have, as he saw fit.

Emotion: empathetic

Cluster: Compassion / Love
PC1 (Valence): 1.55 Positive
PC2 (Disposition): 1.05

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
H0.622
B0.603
L0.529
la0.414
sympat0.393
Suppressed:
iostream-0.441
chẳng-0.393
仿佛-0.359
не-0.352
দুপুর-0.344