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 gallery was empty. David's footsteps echoed on the polished floor. He felt the vastness of the space pressing in on him, the blank canvases a silent judgment. He had once dreamed of this, of showcasing his work. Now, the dream felt hollow.

Then, music. His song, playing from a hidden speaker. It was a stripped-down version, raw and exposed. The musician’s voice was warm, full of heart, but so unfamiliar.

David stopped, his breath catching. He felt a sting behind his eyes. He slowly walked around the gallery, his gaze sweeping over the art. Everything seemed muted, dull. He felt as if he was watching a play, unable to join in. The song ended, leaving a void in the gallery, a void that mirrored the one inside him. He turned and walked out, his steps slow and heavy.

Emotion: lonely

Cluster: Sadness / Despair
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -1.29

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.416
loneliness0.375
孤独0.362
solitude0.351
lonely0.344
Suppressed:
de-0.450
l-0.360
/-0.272
👏-0.262
B-0.241