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 request came via text message, impersonal and cold. "Regarding the tree. Please call when you have a moment." I stared at the words, a wave of nausea washing over me.

The tree in question was a gorgeous willow, and I looked out at it, its weeping branches forming a graceful curtain.

I felt a strange tightness in my chest as I picked up the phone.

The call ended with the neighbor's abrupt suggestion, and I felt a sense of disorientation as I replaced the receiver. I didn't want to engage, and the words had a way of turning my stomach. I turned away from the window, and wandered the rooms, looking for something to focus on.

Emotion: uneasy

Cluster: Fear / Anxiety
PC1 (Valence): -1.80 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.240
😖0.231
😣0.231
느껴0.226
worse0.222
Suppressed:
de-0.474
la-0.465
happy-0.261
a-0.255
ecstatic-0.228