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 attic air tasted of dust and forgotten things, but Eleanor didn't mind. A sunbeam sliced through the gloom, illuminating swirling motes as she rummaged through a trunk overflowing with her mother's belongings. It was a treasure hunt, she decided, a joyous quest to uncover the secrets held captive for years. And then she saw it – a small, leather-bound notebook tucked away in a velvet pouch. Her mother's handwriting, slightly shaky but familiar, danced across the cover: *Bucket List.* A giggle bubbled up from within her, a sound she hadn't made in months.

She flipped through the pages, her heart doing a little skip with each item. “Learn to ride a horse.” “See the Northern Lights.” “Bake a perfect sourdough loaf.” Eleanor felt a grin stretch across her face. This was fantastic! This was a roadmap, a blueprint for adventure, a way to connect with the woman she missed so deeply. She slammed the trunk shut, a sudden surge of adrenaline coursing through her. She was going to do *all* of them.

Emotion: exuberant

Cluster: Positive / Joy
PC1 (Valence): 3.42 Positive
PC2 (Disposition): -0.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.676
de0.605
la0.596
!"0.551
!0.548
Suppressed:
S-0.892
😞-0.474
ness-0.407
L-0.389
😔-0.376