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 arcade pulsed with neon light and the frantic clatter of buttons, and Michael felt a mixture of anticipation and anxiety as he walked in. He'd been designing levels with "LevelLord" in a collaborative online game for months. LevelLord had messaged that he was at the arcade.

He felt a kinship with this person, and an urge to see if the bond was real.

He saw a young man intensely focused on a racing game, his fingers flying over the controls. He was surrounded by a cacophony of sound.

Michael went over, his heart racing. He tapped him on the shoulder.

"Hey," he said, hoping his voice didn’t tremble too much, "Nice game."

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