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 news had been especially bleak, and Ms. Bell felt like the world was crumbling around her. She sat in her empty classroom, the echoes of the day’s lessons a hollow reminder of her own inadequacies. A delivery person had left a small, heavy box on her desk.

Inside, nestled in protective foam, was a collection of art supplies, expensive and high-quality. A note: "For never letting me give up on art. For never letting me give up. - Emily." Emily, who had overcome so much and whose creativity had been so stifled. Ms. Bell carefully touched each item, her sadness dissipating. She thought of Emily's persistence and was filled with a new strength.

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