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 soccer field was a vast green expanse. Javier had always been a midfielder, the engine of the team, the player who linked defense and attack. He was asked to switch to goalkeeper. He knew he didn't have the instincts of a goalie.

The coach, a man he always saw as stoic, had looked at him with an odd mix of appreciation and awkwardness. The primary goalie was out of commission. He felt the weight of the situation on his shoulders.

During training, he saw the other players taking shots, and he felt a sharp pang of anxiety. He understood the pressure of the role, the responsibility of preventing goals, the scrutiny that came with any mistake. He felt a shared sadness.

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