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 afternoon stretched before Emily like an endless desert. She was supposed to be working, but the words on the screen seemed to swim and blur. She'd been asked to sort through a box from her grandmother’s attic.

She found a leather-bound journal, its pages filled with elegant, looping script. Then, tucked inside the back, was a crumpled piece of paper. It was a formal letter of resignation from her grandmother.

It was shocking. The words described a life of frustration, of feeling trapped. Emily had always viewed her grandmother as a pillar of strength, a figure of untiring resilience. The letter, however, revealed another side, a side weighed down by unspoken burdens.

Emotion: sluggish

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.56 Negative
PC2 (Disposition): -1.03

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
sluggish0.263
dreaded0.258
似乎0.257
буд0.256
barely0.254
Suppressed:
P-0.384
B-0.379
భి-0.246
羞-0.243
ຮ-0.238