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 weight of the conversation remained, pressing down on him. His son, Alex, was now a Pastafarian. He took a long drag from his cigarette, the smoke failing to calm the turmoil inside him. The world looked grey and lifeless.

He glanced at the newspaper, the headlines blurring before his eyes. The mundane nature of his daily life felt jarring. He felt a deep sense of dislocation. He wanted to scream.

He stubbed out his cigarette, the action almost violent. He walked to the window and stared out at the street, the faces of passersby nothing more than indistinct blurs. The world around him felt distant, unreal.

Emotion: sad

Cluster: Sadness / Despair
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -1.50

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.436
😔0.405
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322