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).

“Are you even listening, David?” His roommate’s voice snapped him out of his reverie. He sighed, a sound of profound weariness. He had been staring at the wall for twenty minutes, maybe more. Arcadia was closing.

David ran a hand through his hair, mussing it further. He felt a profound sense of isolation, of being adrift without a rudder. His whole world had been turned upside down.

He shook his head and said, "Yeah, I'm listening." But the lie tasted like ash. He was miles away, lost in a swirling vortex of anger and confusion. His roommate kept talking, but David didn't hear a word he said.

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