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).

"Look, Jamie," the manager said, his voice softer than usual. "The team needs a catcher. You’ve got the arm, and the grit…" Jamie gripped the bat tighter, the wood cool against her palm. She’d always seen herself as a pitcher, living for the thrill of the strikeout, the roar of the crowd.

The other players, clustered around, offered a series of encouraging noises. Jamie felt her jaw tighten. She knew how much the team was struggling, the catcher position a constant weakness.

She glanced at the mound, the familiar curve of it, the feeling of power that it gave her, and felt a pang of sadness. Jamie pushed the feeling away, taking a deep breath. She placed the bat on the ground, a single tear escaping her eye. She cleared her throat and nodded.

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