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'd spent the morning staring at the ceiling, feeling an inexplicable hollowness. He'd considered going for a run, but the thought of it was exhausting. He’d flipped through channels on the television, but nothing held his interest. He felt a deep-seated inertia.

He needed something, anything, to break the monotony. His gaze caught on a flyer taped to a telephone pole – a yard sale. It was close by. Without a second thought, he went.

He ambled past the tables, vaguely examining the items. Then, a dark shape caught his eye. A teddy bear, worn and tattered, its button eyes glinting in the sunlight. He knew that bear. A sudden, potent memory, something from his childhood, flickered in his mind.

Emotion: bored

Cluster: Fatigue / Lethargy
PC1 (Valence): 0.04 Positive
PC2 (Disposition): -1.11

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.387
’0.350
unremarkable0.325
दिलचस्प0.323
seemingly0.319
Suppressed:
B-0.592
P-0.304
because-0.292
因为它-0.287
ancar-0.278