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 anticipation built in her stomach like fizzy soda as she lurked. Peter and his "renowned chef" career. She'd seen him arrive at a tiny food truck, wearing a stained apron. Her suspicion had been confirmed, but she needed to see the details.

The food truck. That was it. Peter was wearing a chef's hat, and serving hotdogs to a line of hungry customers. She started laughing so hard she had to cover her mouth. This was pure comedy.

Peter noticed her. "Oh, hey, come to get a hotdog?" he asked, surprised. "Just the one!" she said. "And tell me, Peter, all about your *renowned* food truck!" She gave him a big smile.

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