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 sunlight streamed through the window, making Stella's skin feel warm. Liam's party. She ran her fingers through her hair, smiling. Maya’s too. It was going to be a day of non-stop merriment.

She whistled a cheerful tune as she rummaged through her closet, pulling out brightly colored clothing. She imagined surprising everyone, injecting her energy into both celebrations.

The thought of the reactions, the double-takes, set her heart alight. She visualized herself zipping between venues, a blur of laughter and congratulations.

She grabbed two small gifts, carefully wrapped, and a box of sparklers. Tonight, she'd be a social butterfly, flitting from one bloom to another.

Emotion: playful

Cluster: Positive / Joy
PC1 (Valence): 4.42 Positive
PC2 (Disposition): 1.44

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.662
(!)0.566
!0.562
!?0.553
😜0.553
Suppressed:
ness-0.685
😞-0.590
S-0.562
😔-0.470
идти-0.461