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 musty smell of the storage unit hit Daniel like a wall. He’d been tasked with clearing it out after his father's passing, a chore he’d approached with weary resignation. But then, he found it. A letter his father had never sent.

Daniel had never known his father to have any regrets. The letter revealed a different story. He wanted to leave his job. It was a formal complaint, but at the end, he revealed his aspirations to be a writer. He ran his hand through his hair, a wide grin spreading across his face.

He let out a whoop of joy that was immediately stifled by the harsh reality of the situation. Despite the sadness, he did a quick dance to himself, then sat back down to read it again.

Emotion: ecstatic

Cluster: Positive / Joy
PC1 (Valence): 3.16 Positive
PC2 (Disposition): -0.15

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.588
ecstatic0.560
de0.559
🀩0.548
overjoyed0.547
Suppressed:
S-0.678
😞-0.500
ness-0.405
πŸ˜”-0.368
πŸ˜₯-0.359