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 scent of oil paints and turpentine once enveloped Elena's world. Art was her passion, her solace, her way of seeing the world. Now, she felt a profound change. Her daughter, nine-year-old Sofia, had begun painting as well.

Sofia's artwork had grown, improved. Her work now filled their tiny apartment. Elena watched Sofia’s progress, a quiet mix of pride and something that felt like a quiet ache.

Elena knew exactly what it felt like.

"What do you think of this, Mom?" Sofia asked, holding up a canvas.

Elena examined the painting, a vibrant landscape filled with bold colors. She was silent, her fingers tracing the air.

"It's...beautiful," she said, her voice catching slightly. "Really beautiful."

Emotion: sympathetic

Cluster: Compassion / Love
PC1 (Valence): 1.13 Positive
PC2 (Disposition): 0.75

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
H0.521
L0.421
B0.401
la0.338
sympat0.305
Suppressed:
iostream-0.334
简直-0.306
再び-0.305
chẳng-0.296
не-0.296