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 stared at the spreadsheet, rows and columns of numbers blurring before his eyes. The numbers held no meaning, no weight. The air conditioning hummed, a monotonous drone that amplified the emptiness in the room. He rubbed his temples, a dull ache throbbing behind his eyes.

The construction crew next door was loud and irritating, yet their work was captivating. Each swing of the hammer a small drama. Each board nailed on was a small, satisfying completion.

He shoved back from his desk, the chair screeching on the polished floor. He felt a profound sense of… something akin to restlessness. He needed to get out. He needed… something. He stood and walked toward the window, looking at the workers.

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