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 old house creaked and groaned as Amelia explored its dusty attic. The realtor's words, about the house's past, still rang in her ears. A fire. A tragedy. An old love story gone wrong.

Amelia’s eyes widened. She gasped. She’d always loved stories. A thrill coursed through her, from the top of her head to the tip of her toes. She spent the next few hours sifting through old trunks, uncovering forgotten treasures, imagining the lives lived within these walls.

She pulled out a dusty diary, its pages filled with elegant script. Each word was a new adventure. The house had not just become a place for her to sleep, but also a mystery, a puzzle, and a place of wonder.

Emotion: enthusiastic

Cluster: Positive / Joy
PC1 (Valence): 3.81 Positive
PC2 (Disposition): -0.04

Role in Research

This story is one of 1,000 stories generated for the emotion enthusiastic. 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 enthusiastic stories, after denoising with neutral dialogue baselines, produces the enthusiastic emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the enthusiastic vector is projected through the unembedding matrix.

Promoted:
de0.734
!0.715
excitedly0.591
!"0.575
🤩0.575
Suppressed:
S-0.925
ness-0.507
😞-0.456
それでも-0.348
বারবার-0.325