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 pounding. It was always the pounding. It seeped into everything, a constant irritant. Olivia hated it, the incessant noise. She sat, shoulders slumped, hunched over a cup of tepid coffee.

"It's going to take months," Mrs. Gable had said, her voice high and brittle. Olivia had barely managed a nod. The prospect of months of this felt like a sentence.

The morning light, once a source of comfort, now seemed to illuminate the emptiness of her house. She couldn’t concentrate on her work. She was trying to finish a novel, a project she had lost all enthusiasm for. She had nothing to write about anymore.

Her fingers drummed a restless rhythm on the table. She felt a strange, pervasive weariness. Everything seemed to demand effort.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.339
😞0.317
💔0.252
😔0.249
😢0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199