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 sudden lightness in Emily’s chest was almost intoxicating. She’d been feeling so down lately, stuck in a rut. But the sight of Mr. Peterson, normally clad in faded jeans, emerging from a private jet at the local airstrip, changed everything. She gripped the steering wheel so hard her knuckles were white.

A giggle escaped her lips. She felt like she could fly. She imagined the things she could do, the places she could go. A new wardrobe, a career change, the ability to finally pursue her art seriously. Freedom!

She drummed her fingers on the steering wheel, completely unable to contain herself. She needed a new plan. Her mind was a whirlwind of ideas as she started the car and practically flew down the road.

Emotion: exuberant

Cluster: Positive / Joy
PC1 (Valence): 3.42 Positive
PC2 (Disposition): -0.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.676
de0.605
la0.596
!"0.551
!0.548
Suppressed:
S-0.892
😞-0.474
ness-0.407
L-0.389
😔-0.376