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).

"A hamster!" Finn declared, his voice brimming with uncontainable enthusiasm. He was sprawled on the couch, feet in the air, imagining tiny paws scurrying inside a clear plastic ball. He clapped his hands together, his grin stretching from ear to ear. "Imagine the adventures! We could build him a miniature obstacle course!"

Kai, perched on the edge of the coffee table, was not amused. He adjusted his glasses, his tone measured. "Finn, we have a meticulously organized apartment. A hamster is a furry little tornado of mess and chaos."

Finn leapt off the couch, bounding towards the kitchen, and grabbed a random spatula, pretending to feed the spatula some imaginary hamster food. "He could be our little buddy!" He squealed, then proceeded to make chattering noises.

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