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 windows as Amelia stared at the final chapter, a fictionalized account of their last argument. Her chest felt constricted, a tight band around it that made it difficult to breathe. The protagonist, a mirror image of herself, was depicted with such vivid, heartbreaking detail. It showcased her petty frustrations, her impulsive decisions that always seemed to backfire.

She ran a hand through her hair, a sigh escaping her lips. She could feel his intentions. He meant no harm.

The coffee table in front of her seemed to be a mile away. She closed the laptop, a heavy feeling settling in the pit of her stomach. The pain in his fictional words was sharp. She understood the effort.

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