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).

Daniel found the letter tucked amongst his grandfather's tools in his old workshop. The letter was a draft resignation to a local factory where he had worked for decades. The letter detailed the monotony, the physical toll, and the longing for something more. Daniel, reading it, felt a sudden surge of… something akin to empathy.

He’d known his grandfather as a gruff, practical man, always fixing things, never complaining. The letter presented a different facet. He ran a hand across his beard, his throat constricting. He imagined his grandfather, weary but resolved, making this decision.

He gently placed the letter back amongst the tools, feeling a newfound respect for the man he had known. The room suddenly seemed filled with a new type of understanding.

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