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 attic air hung thick with dust motes dancing in the sunbeams. Amelia coughed, waving a hand in front of her face as she rummaged through a trunk overflowing with forgotten treasures. Her fingers brushed against brittle paper. A draft letter, typed on a typewriter, dated from 1988. It was her mother’s handwriting in the signature block. Her pulse quickened.

She scanned the words. A resignation! From the law firm her mother had worked for before Amelia was born. Abandoning a career she’d always made sound so important. A giddy laugh bubbled up her throat.

"Wow," she breathed, rereading the final paragraph. It spoke of creative stagnation, a yearning for something more. Amelia’s fingers trembled as she folded the fragile paper, a huge grin plastered across her face. This was better than finding a winning lottery ticket.

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