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 air conditioning blasted, creating a bone-chilling cold that seemed to seep into his very core. He hated this. He hated the forced cheerfulness. He hated the vacant smile he was supposed to wear. He knew he had to teach. And he hated it.

"Okay," he said, his voice flat. "Let's begin." He pointed a finger at the screen, a mechanical gesture. He could feel the tension building in his shoulders, a physical manifestation of his internal resistance.

He watched the new recruit, Jessica, navigate the system. A dark cloud seemed to settle over him. She was young, so full of energy. A stark contrast to his own fatigue. He felt a deep weariness, a longing for… what? He didn’t know.

Emotion: brooding

Cluster: Sadness / Despair
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.60

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.749
😞0.329
그의0.299
un0.273
但他0.270
Suppressed:
de-0.917
la-0.603
a-0.369
l-0.335
her-0.330