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 air in the house was thick with unspoken sadness, the silence echoing through the empty rooms. Then there was a knock. When I opened the door, it was Ms. Rodriguez, the woman from next door. She held a basket brimming with seedlings.

"I was wondering," she began, a tentative note in her voice, "If I could perhaps use a small patch of your lawn?" The words seemed to float around me, like a bad smell. I tried to focus, but the world seemed blurry.

I stared at the plants, their vibrant greens mocking my own stillness. I managed a weak nod. The weight in my chest felt heavier with the agreement. I just wanted her to leave.

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
いつも0.238
😔0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239