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 sound of the crash woke me. Even through the closed window, the noise had been enormous. When I peered outside, I saw the massive pine tree that bordered the Peterson's property had split and half of it landed on their fence.

I threw on clothes and raced outside, heart pounding. I saw Ms. Peterson, standing near the wreckage, her hands covering her mouth. I could sense her overwhelm.

"Are you okay, Marie?" I called out, hurrying towards her. She shook her head, unable to speak. The sheer scale of the mess seemed to have silenced her.

I spent the whole morning with her, working on the fence, offering to help with cleanup, and calling around for a professional arborist to assess the damage.

Emotion: compassionate

Cluster: Compassion / Love
PC1 (Valence): 3.19 Positive
PC2 (Disposition): 1.62

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.811
B0.618
H0.550
sympat0.422
latter0.422
Suppressed:
此刻-0.519
не-0.514
솟-0.446
désormais-0.446
仿佛-0.444