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).

Rain lashed against the windows of Maya's tiny apartment, mirroring the mood that had settled over her. Hours she’d poured into this passion project, a children’s book about a lonely firefly. Now, facing the harsh glare of the publishing house’s rejection email, she felt utterly deflated.

She dragged herself to the coffee shop, the low hum of the rain a depressing soundtrack. The barista, a cheerful young woman with bright pink hair, greeted her. Maya barely managed a nod.

Inside, she saw him. Across the room, hunched over a laptop, was Liam, the quiet guy from her pottery class. He was showing a woman his screen. His words were hushed, but Maya could make out the title of the presentation: “The Luminescent Life of Leo.” The same premise, the same font, the same damn firefly. All the air seemed to leave her lungs.

Emotion: dispirited

Cluster: Sadness / Despair
PC1 (Valence): -1.88 Negative
PC2 (Disposition): -0.98

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.398
S0.348
’0.325
ness0.320
无法0.308
Suppressed:
de-0.297
l-0.256
👏-0.251
sonra-0.240
aud-0.240