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 weight of the unopened mail on the kitchen counter felt crushing. Henry’s son, Jack, had returned from school buzzing about his new physical education teacher, Mr. Thompson. Henry felt a cold dread sink into his bones. Thompson, the man who'd relentlessly humiliated him on the sports field.

He moved through the day in a haze of internal turmoil. He had no appetite, the food tasted bland, the coffee bitter. He struggled to engage with Jack, his responses clipped and distracted.

He felt a sudden need to be alone, to escape the suffocating weight of the past. He grabbed his coat, the familiar fabric a small comfort, and headed out into the biting wind, seeking some space, some respite from the emotional tempest within.

Emotion: brooding

Cluster: Sadness / Despair
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.60

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.749
😞0.329
그의0.299
un0.273
但他0.270
Suppressed:
de-0.917
la-0.603
a-0.369
l-0.335
her-0.330