The hardest part of a dissertation is not the research. It's finding the question. I'm a third-year PhD student in organizational behavior, and by the end of my sixth week of reading I had reached a very specific kind of rock bottom: convinced that everything interesting about work motivation had been studied by someone more qualified than me, published somewhere I'll never reach, and probably replicated twice for good measure. I called my advisor in a tone she later described, charitably, as 'pre-spiral.'
Her advice should have come in year one: 'Stop reading for what we know. Start reading for what we don't.' It's obvious in hindsight and impossible to actually do when you're drowning. You can't read for absence — your brain keeps grabbing onto the presence of things, the studies that exist, the findings that are there. What I needed was something that would systematically ask 'what's missing here?' of a body of work I'd already collected.
Turning a 40-page review into a gap map
I took the most comprehensive thing I'd found — a 40-page meta-analysis on self-determination theory in workplace settings — and ran it through Gemini 3 Pro Preview with the Find the Real Gaps in a Literature Review prompt, field set to 'organizational behavior' and research goal set to 'identify a viable dissertation topic.' I used Gemini deliberately: a 40-page review is a long-context job, and Gemini chews through long documents and returns a clean comparison table without losing the thread halfway down the page. The prompt asks for a GAP MAP table, which turned out to be exactly the right shape — five categories of gap, side by side, each rated for tractability.
The 'Understudied Population' row named something I'd half-noticed for weeks and never managed to articulate: nearly every study in the meta-analysis used full-time, permanent employees at Western firms. Contract workers, gig workers, and non-Western contexts were barely present, and where they showed up they were a footnote about generalizability. The Evidence-in-Text column pointed me to the exact sentences in the review where the authors mentioned, almost in passing, that their samples skewed this way. The tractability was rated High — standard validated survey scales would work, and the population is reachable through gig-work platforms. That 'High' is what turned a vague unease into a project I could actually start on Monday rather than someday.
What got me was that I had read that meta-analysis. Twice. The sentences the Evidence-in-Text column quoted back at me were sentences my own eyes had passed over, because I was reading for findings — for the satisfying 'they discovered X' moments — and these were limitations, the part of a paper your brain treats as throat-clearing. The gap wasn't hidden. It was sitting in plain sight in a section I'd been trained, by years of reading for results, to skim. The prompt's only real magic was reading the part I'd taught myself to ignore.
From a row in a table to a real question
A gap is not yet a question. The TOP THREE DIRECTIONS section did the bridging. It sketched a study: does self-determination theory predict motivation differently for contingent workers, who lack the job security the theory's evidence base assumes? I brought exactly that to my advisor, who has a finely calibrated detector for 'student is grasping' versus 'student has something.' She said, 'That's a real question. Write the proposal.' I have heard her say the first half of that sentence many times. The second half was new.
- The gap: self-determination theory was mostly tested on permanent, secure, Western employees
- The question: does it hold for gig workers whose insecurity violates the theory's hidden assumptions?
- The tractability: High — validated scales exist, the population is reachable, the comparison is clean
- The caveat I respected: confirm against a primary database search before committing — which I did, and it held
Here's the honest part: the prompt did not find my topic. It found the shape of what hadn't been done, in a body of work I'd already read but couldn't see clearly because I was reading for the wrong thing. After six weeks of cataloguing what existed, having something map the holes was the difference between spiraling and starting. I'm now nine months into a dissertation on motivational dynamics among gig workers, and the GAP MAP for that original review is still pinned above my desk, a little smug.
If you're staring at a literature review certain that every good question is taken, you're reading it the way I was. Grab the Find the Real Gaps in a Literature Review prompt on Prompt Dock, feed it the densest review you've got, and let it show you the absences. Then run my Create a Reproducible Search Strategy for a Systematic Review prompt to actually go confirm the gap is real before you bet two years on it.