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 cold steel pressed against her back as she leaned against the wall. Hours ticked by, each passing moment a painful reminder of her solitude. She imagined her small apartment, tidy and quiet, waiting for her return. She used to look forward to the solitude. Now, it felt like punishment.

Her coworker, David, a man she barely knew, was trying to make small talk. She attempted a smile, but it felt stiff and unnatural. She wanted to be left alone, but the oppressive silence was worse.

“So, you like hiking, right?” David asked, attempting to make conversation. She nodded, her throat tight. She wished he'd just be quiet.

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