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 phone lay silent on the table, another evening passing without a call from Michael. The apartment, usually filled with the aroma of his cooking, was eerily empty. Thomas felt a deep, pervasive sense of unease. He wandered from room to room, touching objects, the familiar textures offering no comfort.

While sorting through a drawer, he found a small, leather-bound book with a gold-leaf inscription: "Before the World Changes." He flipped through the pages with a growing sense of dread.

One item, written in bold letters, stood out: "Attend a live music performance with Thomas." Michael loved music; they had always talked about it. He felt his face flush with a wave of unexpected shame. They hadn't gone out in months.

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