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).

"Hey, Sarah, you okay?" Mark asked, his brow furrowed with concern. He knew. Everyone knew. He’d found her hunched in the corner of the student cafeteria, picking at a plate of fries. The usual zest with which she devoured the over-salted potatoes was gone. Her fork moved listlessly, barely making contact with her food.

"Fine," she mumbled, but her voice lacked its usual energy. He knew it was a lie. Her eyes were red-rimmed. She'd been so excited about the upcoming theatre production. Now, the thought of rehearsals and performances seemed like a chore. All the enthusiasm he knew her for was gone and replaced with a sense of utter weariness.

Emotion: droopy

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.15 Negative
PC2 (Disposition): -1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.303
无法0.252
い぀も0.238
πŸ˜”0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239