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).

Sarah couldn't stop grinning. Her cheeks ached, but she didn’t care. Finally! Mr. Henderson, with his endless barking dog and habit of 'borrowing' her garden gnomes, had relented. A fence was going up.

She grabbed her phone and immediately texted her best friend, "OMG, it's happening! No more dog poop in my petunias!"

A shiver of pure glee ran through her. It was a victory, a monumental one, and she could feel the tension she'd been carrying for months simply evaporate. She began cleaning her house, humming a song that she heard on the radio this morning.

Her hands moved with a furious energy, dusting, vacuuming, and straightening, fueled by the prospect of a more peaceful existence.

Emotion: ecstatic

Cluster: Positive / Joy
PC1 (Valence): 3.16 Positive
PC2 (Disposition): -0.15

Role in Research

This story is one of 1,000 stories generated for the emotion ecstatic. 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 ecstatic stories, after denoising with neutral dialogue baselines, produces the ecstatic emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the ecstatic vector is projected through the unembedding matrix.

Promoted:
!0.588
ecstatic0.560
de0.559
🤩0.548
overjoyed0.547
Suppressed:
S-0.678
😞-0.500
ness-0.405
😔-0.368
😥-0.359