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).

"Yes!" Mark practically yelled, startling the barista. He'd just gotten the call confirming his promotion, and a wave of pure elation surged through him. He paid for his coffee, practically vibrating with energy.

He practically skipped out of the coffee shop, a goofy grin plastered on his face. The city seemed brighter, the air crisper. He practically felt like he could run a marathon. He’d decided to head to the gym for a celebratory workout.

And there he was. Sarah, arms crossed, looking at a framed photo. Sarah, who’d made his life a misery. Sarah who was now, according to a tasteful plaque, "Dr. Sarah Bellweather, Trauma Specialist." A bubble of laughter escaped his lips. The world, somehow, got even funnier.

Emotion: joyful

Cluster: Positive / Joy
PC1 (Valence): 3.96 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.615
de0.600
!0.572
excitedly0.552
enthusi0.533
Suppressed:
S-0.893
ness-0.513
😞-0.470
😣-0.337
L-0.334