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).

"This is going to be good," Chloe murmured, rubbing her hands together with glee. "Remember the time we tried to build a raft and sail down the creek?" She raised an eyebrow. "Epic fail, or glorious adventure?"

Daniel, meticulously arranging his tools in the shed, sighed dramatically. "It was a disaster. The raft sank within minutes. We looked like drowned rats."

Chloe let out a whoop of laughter, clapping her hands. "But the *build-up*! The ingenuity! We thought we were proper explorers!" She imagined them on their raft.

"I recall a lot of splinters and frantic paddling," he said, turning to face her, a matching grin starting to spread across his face. "You, on the other hand, were already planning our next expedition."

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
πŸ˜”-0.470
ΠΈΠ΄Ρ‚ΠΈ-0.461