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).

"Wow." That was all Sarah could manage at first, staring at the list in her hands. It was folded neatly, tucked inside a card he’d given her on their anniversary. It was marked “My Bucket List (For Us!).” A shiver of something like delight went down her spine.

‘Go stargazing.’ ‘Learn to dance.’ ‘Adopt a dog.’ She read each item with a growing sense of wonder. This was… everything. The air felt charged with possibility, the ordinary world transformed into a vibrant tapestry of shared dreams.

She pictured them, hand-in-hand, under a canopy of stars. Learning to waltz, giggling, tripping over each other's feet. Her heart swelled, a joyful ache within her chest. She couldn't wait to start.

Emotion: elated

Cluster: Positive / Joy
PC1 (Valence): 3.38 Positive
PC2 (Disposition): -0.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.724
!0.596
ecstatic0.510
🤩0.510
overjoyed0.504
Suppressed:
S-0.657
😞-0.497
ness-0.407
😔-0.380
😓-0.377