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 break room felt thick, heavy with the scent of stale coffee and unspoken questions. Across the table, Emily was animatedly describing her summer at "Camp Skylark," a summer camp she loved.

I found myself struggling to breathe. The details – the rickety wooden cabins, the peculiar rules, the nightly sing-alongs – were all too familiar. A sense of disquiet settled over me, a feeling that something was profoundly off. The room started to spin.

"Skylark?" I asked, my voice barely above a whisper.

Emily paused. "Yeah, what's wrong? You look pale."

I just stared at her, my mind reeling. My eyes stung with unshed tears.

Emotion: mystified

Cluster: Surprise / Confusion
PC1 (Valence): -1.24 Negative
PC2 (Disposition): -0.16

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
que0.458
🤔0.364
🤔0.357
будто0.308
puzzling0.299
Suppressed:
alleviate-0.241
ecstatic-0.232
timeLeft-0.232
rest-0.227
allevi-0.225