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).

Ms. Abernathy practically bounced into the staff room, her floral skirt swirling around her ankles. A bright, sunny morning had arrived, and she felt like she could leap over the mountains. She hummed a jaunty tune as she reached for the coffee pot, her fingers tapping a lively rhythm on the counter. Today was going to be brilliant, she simply knew it.

A package, bearing a familiar return address, sat on her desk. Curiosity bubbled within her. Her breath hitched slightly as she tore it open. Inside, nestled in tissue paper, was a hand-painted portrait of herself, beaming. It was from Emily Carter, a student she'd encouraged years ago to pursue her art.

A whoop of pure delight escaped her lips. She dashed out of the staff room, eager to show off her unexpected treasure.

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