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 scent of coffee hung heavy in the air as Maya poured herself a second cup. The laptop sat open on the kitchen counter, its screen displaying the latest chapter of David’s novel, “The Girl with the Tattoo." Each paragraph was a new explosion of delight. She felt weightless, like she could float away.

She had found it while looking for a recipe, her fingers accidentally clicking on a file labeled "Project." She hadn't been able to resist. The description of her, her personality, her quirks — it was all him, all David, capturing her essence. She felt a lightness in her chest, a feeling that she could do anything.

A laugh escaped her, followed by a series of happy little noises. The mundane task of making coffee felt charged, full of vibrant life. She spun around, humming a little tune, and began to tidy up the kitchen with an energy she hadn't felt in weeks. She could hardly wait to tell him.

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