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).

From his perch on the park bench, Arthur watched the children chase pigeons, their laughter echoing through the air. He felt a profound sense of… detachment. The world seemed to be moving at a different speed than he was. He’d walked through the park, noting the changing seasons, the rustle of leaves, but it all felt distant, a muted film playing on a screen. He opened the book he'd borrowed from the library, a collection of short stories by an author he'd never heard of. He glanced at the words, but they didn’t penetrate.

A small envelope, tucked inside, fell to the ground. He picked it up. Inside, a photograph of a smiling couple and a handwritten note: "The best days of my life." The simplicity of the message, the quiet joy captured in the image, resonated with a deeper part of him. He traced the outline of the photograph with his finger, finally feeling a tiny shift, a slight alteration in the landscape of 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