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 bell above the pawn shop announced her arrival with a cheerful jingle, and Emily almost skipped inside. A grin plastered itself across her face, refusing to be budged. She couldn’t help it. The prospect of what lay ahead filled her with an incredible lightness, a feeling akin to being weightless.

The shop owner, a man with a perpetually tired expression, barely looked up from his newspaper. “Whatcha need?”

“The ring,” she said, her voice breathy. “The… the gold one with the amethyst. I saw it online.” She felt utterly fantastic.

He pointed, a flicker of something almost resembling interest in his eyes. There, nestled amongst the other treasures, it lay.

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