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).

He slammed the gym door, the air inside immediately thick with the smell of sweat and iron. His muscles ached, but it was a welcome pain, a distraction from the turmoil inside him. The news of his half-sister had landed like a punch to the gut. He’d gone numb, disconnected from the world.

He attacked the punching bag with ferocious energy, each strike a frustrated shout. He imagined his father, always so careful, so guarded, his secret finally exposed. The irony was bitter. He'd dedicated his life to achieving the opposite: complete honesty.

His breath came in ragged gasps. He dropped to the floor, his head swimming with the implication: a hidden life, a whole other family. A dark shadow fell over his usual cheerful demeanor. A wave of exhaustion washed over him.

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