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 scent of freshly brewed coffee, usually a comfort, was now a challenge. Across the fence, the wealthy, reclusive Mr. Harding was having a brunch *every* Saturday. Amelia noticed the expensive cars, the impeccably dressed guests, the laughter that floated over the fence. She felt a tickle of something in her stomach.

She decided to cultivate a new interest: the art of the perfect picnic. Armed with a checkered blanket and a basket overflowing with homemade goodies, she set herself up directly across from Mr. Harding’s backyard. She meticulously arranged her picnic, making sure every detail was perfect.

She caught Mr. Harding’s eye. She smiled, a broad, innocent smile. This was going to be fun.

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