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 bass from next door rattled the photographs on my mantelpiece. Each picture was a memory, a ghost of a past that seemed increasingly distant. I stared at the smiling faces, feeling a pang of longing.

I made the decision to go and knock on his door. When it opened, a tall, smiling man with a bright shirt stood before me. I opened my mouth, but only a croak emerged.

“Yes?” the man asked, his eyebrows raised.

“Could you…could you turn the music down a bit?” I finally managed. My voice sounded small and insignificant.

He nodded, a flicker of surprise in his eyes. I turned and walked back inside, the music slightly softer, but still there.

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