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 attic air hung thick and still, dusty sunlight slanting through a crack in the boarded-up window. A single moth flitted erratically around the rafters. Amelia sighed, her shoulders slumping. Summer stretched before her, an endless expanse of unscheduled time. She ran a hand over the overflowing cardboard boxes, a futile gesture. A vague sense of stagnation settled in her chest.

She pulled the lid off the first box, the musty scent of forgotten things filling her nostrils. Then, a gleam of recognition: her mother's handwriting. Elementary school assignments, meticulously filed. She picked up a slightly crumpled book report, a childish drawing of a very lopsided sun peeking over a tree accompanying the text.

Amelia found herself smiling, a genuine, unforced expression. Maybe this was something to do.

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