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).

Rain lashed against the window as Eleanor watched her nephew, Leo, meticulously color a picture. He was drawing the same absurdly long-limbed creature she'd conjured as a child, though now it bore the name “Flibbertigibbet.” A warmth spread through Eleanor's chest; a feeling that made her want to wrap Leo in a blanket.

She watched as Leo’s tongue poked out in concentration. Eleanor felt a visceral connection to the child, a sudden wave of tenderness, seeing him absorbed in his creation. "He looks very important," she remarked, her voice gentle as she reached out a hand to stroke his hair.

That night, she reread her old journal, filled with sketches of Flibbertigibbet. A smile played on her lips. She felt a profound connection to the child she once was.

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