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).

“Dad, are you sure you’re okay?” Leo asked, his voice hesitant. He’d found the letter in a box of old photos. His father, now a jovial man of retirement, had once contemplated leaving his entire career. Leo felt a coldness creeping through him.

His father merely smiled, a fleeting expression that seemed almost fragile. Leo watched him, a slow ache building in his chest. He felt compelled to fill the void, to speak, to share the burden of this knowledge.

But instead, he just stood there, the letter burning a hole in his pocket. The air inside the living room felt too thin, too close. He took a step back, the words swimming in his head.

Emotion: unsettled

Cluster: Fear / Anxiety
PC1 (Valence): -2.33 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.382
😞0.309
ness0.301
😣0.256
😔0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274