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 cafeteria buzzed with the usual Friday afternoon chatter, but the atmosphere felt strangely muted. I watched Sophia, head down, picking at her food. The accusation, a shadow that had fallen over her, seemed to cast a pall over everything.

I recalled my own academic struggles, the moments of near-breaking, the feeling of being utterly lost. I imagined the panic, the fear, and the shame she must be feeling. A wave of nausea hit me, as if I had eaten something that disagreed with me.

Her hand trembled as she lifted a forkful of salad to her mouth. I could see how she wanted to retreat and disappear.

I walked over to her table. "Mind if I join you?" I asked, my voice softer than usual.

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