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 relentless sun beat down on him, but it brought no warmth. Ethan felt chilled to the core. He moved through the day with a sluggishness that bordered on paralysis. He'd lost interest in everything. The vibrant colors of the world seemed faded, the sounds muffled. He was a shell.

He drifted into a pawn shop, the air inside thick with the scent of old things. He wasn't looking for anything, just seeking a momentary distraction from the dull ache inside. Then, he saw it: a ring, a familiar, distinctive setting.

He asked the proprietor, a man whose face was etched with a permanent frown, to see it. He picked it up and saw the inscription: "Forever, With You." He traced the letters with his finger, a knot tightening in his stomach. The realization hit him like a physical blow. It was her ring. How on earth?

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