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 low thrum of the lawnmower vibrated through David's chest as he meticulously trimmed his grass. Every blade was perfectly aligned, a testament to his dedication. Barnaby, sensing an opportunity, wriggled under the fence and charged into his yard. David switched off the machine and sighed, a grin spreading across his face.

“Alright, buddy. Let’s play fetch.” He grabbed Barnaby's favorite squeaky ball. The dog's ears perked up, eyes locked on the prize. David's chest swelled with a familiar feeling, a sense of having things just right. Throwing the ball and watching Barnaby chase after it, the world seemed balanced, orderly, and complete.

Emotion: fulfilled

Cluster: Positive / Joy
PC1 (Valence): 3.22 Positive
PC2 (Disposition): -1.74

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.819
மகி0.415
happy0.397
grateful0.389
de0.385
Suppressed:
S-0.599
worse-0.465
C-0.460
either-0.436
😣-0.426