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 setting sun cast long shadows across the dusty bookshelves of her home office. Elizabeth, perched on a ladder, was attempting to find a specific edition of Jane Eyre. Her search was interrupted by the discovery of a small, leather-bound diary tucked away at the back. It was her own handwriting, from what must have been her early teens. She couldn't help but feel a sudden surge of something wonderful.

She opened the diary, her eyes scanning the faded ink. It seemed she'd been an optimist. "Dear Diary," she read aloud, with a flourish, "Today, I decided to become a pirate. I think I will start by stealing all the cookies..."

A delighted, bubbling sensation began in her chest. She climbed down the ladder and decided to have a biscuit herself.

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