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).

β€œOh, bother,” muttered Sarah, her fingers coated in a layer of grime from the garden shed. She had been searching for a lost gardening trowel, but the discovery of a sealed envelope, addressed in a familiar hand, immediately captivated her attention. Her curiosity piqued, she felt a sudden urge to open it.

She ripped it open. Inside, a single sentence, scrawled in her younger, more flamboyant writing, caused her face to crack into a grin. "Roses are red, violets are blue, and I'm about to put glue in your shoe."

Sarah imagined her younger self, plotting mischievous schemes with friends. The feeling of that carefree energy returned to her in waves.

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