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).

Zara had seen the tattoo before she saw the artist. He’d been working at a gallery show she was attending. She saw it first, etched across his sternum: her abstract piece, "Chromatic Drift," rendered in a stunning array of colours.

She approached him slowly, her palms sweating. “I…I designed that,” she managed, her voice shaky. He looked up, startled, then a slow smile spread across his face.

"It's beautiful," he said. Zara felt a strange sense of relief, a melting of the tension that had been building inside her. She understood the need to make something permanent, to carry a piece of beauty with you always. It was a shared experience of sorts.

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