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).

"Oh, bother," Maya declared, her voice light and airy. Her eyes danced with a peculiar glee as she beheld the empty space where her ancient Volvo had been parked. She'd been meaning to get it serviced, anyway. A perfect excuse!

She grabbed a nearby garden gnome and set it in the middle of the empty space. "Guard the fort, Bartholomew!" she commanded, her lips twitching with suppressed mirth. Her fingers drummed a rhythm against her thigh.

She spent the next hour documenting the whole episode, texting her friends with emojis and exclamation points. This was going to be a phenomenal story.

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