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).

"Alright, here we go!" Clara sang, practically skipping towards the old park. The anticipation was intoxicating. She had visions of her tree, grown tall and strong, a testament to her childhood dreams. She had plans for a photoshoot.

Her breath hitched. A hollow space greeted her. A single, sawed-off trunk stood, a monument to…what exactly? A flicker of… something… moved behind her eyes. A sense of…unpleasantness… bubbled up from the pit of her stomach. The photoshoot idea? Vanished.

Clara traced the ring of the stump, a knot forming in her throat. She bit back a wave of something. She wasn’t sure what to do with the day anymore.

She shrugged, a strange tightness in her chest. Back to the car.

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